Article(id=1327018631696855099, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327018536993665336, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202440265, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1713369600000, receivedDateStr=2024-04-18, revisedDate=1739721600000, revisedDateStr=2025-02-17, acceptedDate=1740931200000, acceptedDateStr=2025-03-03, onlineDate=1794315496610, onlineDateStr=2026-11-10, pubDate=1753977600000, pubDateStr=2025-08-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794315496610, onlineIssueDateStr=2026-11-10, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794315496610, creator=13701087609, updateTime=1794315496610, updator=13701087609, issue=Issue{id=1327018536993665336, tenantId=1146029695717560320, journalId=1324759914146529478, year='2025', volume='62', issue='8', pageStart='1833', pageEnd='2124', issueExtLink='null', onlineDate='null', pubDate='1753977600000', pubDateStr='2025-08-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794315474031, creator='13701087609', updateTime=1794376881014, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1327276097470837643, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327018536993665336, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1327276097470837644, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327018536993665336, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=1979, endPage=2018, ext={EN=ArticleExt(id=1327018631906570300, articleId=1327018631696855099, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Survey on Security and Privacy Risks in Large Language Models, columnId=1325493671541474142, journalTitle=Journal of Computer Research and Development, columnName=Network and Information Security, runingTitle=null, highlight=null, articleAbstract=
In recent years, large language models (LLMs) have emerged as a critical branch of deep learning network technology, achieving a series of breakthrough accomplishments in the field of natural language processing (NLP), and gaining widespread adoption. However, throughout their entire lifecycle, including pre-training, fine-tuning, and actual deployment, a variety of security threats and risks of privacy breaches have been discovered, drawing increasing attention from both the academic and industrial sectors. Navigating the development of the paradigm of using large language models to handle natural language processing tasks, as known as the pre-training and fine-tuning paradigm, the pre-training and prompt learning paradigm, and the pre-training and instruction-tuning paradigm, this article outlines conventional security threats against large language models, specifically representative studies on the three types of traditional adversarial attacks (adversarial example attack, backdoor attack and poisoning attack). It then summarizes some of the novel security threats revealed by recent research, followed by a discussion on the privacy risks of large language models and the progress in their research. The content aids researchers and deployers of large language models in identifying, preventing, and mitigating these threats and risks during the model design, training, and application processes, while also achieving a balance between model performance, security, and privacy protection.
, authors=Yi Jiang
1, 2, Yong Yang
1, Jiali Yin
3, Xiaolei Liu
4, Jiliang Li
5, Wei Wang
6, Youliang Tian
7, Yingcai Wu
1, Shouling Ji
1, *, authorsList=Yi Jiang, Yong Yang, Jiali Yin, Xiaolei Liu, Jiliang Li, Wei Wang, Youliang Tian, Yingcai Wu, Shouling Ji, authorCompany=null, correspAuthors=Shouling Ji, authorNote=
born in 1982. PhD candidate. Member of CCF. His main research interests include data-driven security and privacy, and AI security
born in 1996. PhD candidate. Member of CCF. His main research interest includes AI security and privacy
born in 1993. PhD, professor, PhD supervisor. Member of CCF. Her main research interests include computational photography, deep feature fusion interpretability of neural networks, adversarial training
born in 1992. PhD, associate professor. Member of CCF. His main research interests include equipment information security and AI security
born in 1989. PhD, professor, PhD supervisor. Member of CCF. His main research interests include network and information security, AI security, and large language model security
born in 1976. PhD, professor, PhD supervisor. Distinguished member of CCF. His main research interests include cyberspace and system security, and blockchain and privacy preservation
born in 1982. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include cryptography and security protocols, big data security, and privacy protection
born in 1983. PhD, professor, PhD supervisor. Senior member of CCF. His main research interest includes visual analytics
born in 1986. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include data-driven security and privacy, AI security, and big data mining and analytics
, correspAuthorsNote=null, copyrightStatement=Copyright © 2025 Journal of Computer Research and Development. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1327018635991822433, articleId=1327018631696855099, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=大语言模型安全与隐私风险综述, columnId=1325493672690713440, journalTitle=计算机研究与发展, columnName=网络与信息安全, runingTitle=null, highlight=null, articleAbstract=
近年来,大语言模型(large language model,LLM)作为深度学习网络技术的关键分支,在自然语言处理(natural language processing,NLP)领域取得了一系列突破性成就,并被广泛采用. 然而,在其包括预训练、微调和实际部署在内的完整生命周期中,多种安全威胁和隐私泄露的风险相继被发现,引起了学术和工业界越来越多的关注. 首先以LLM发展过程中出现的预训练-微调范式、预训练-提示学习范式和预训练-指令微调范式为线索,梳理了针对LLM的常规安全威胁,即3种对抗攻击(对抗样本攻击、后门攻击、投毒攻击)的代表性研究,接着总结了一些最新工作披露的新型安全威胁,然后介绍了LLM的隐私风险及其研究进展. 相关内容有助于LLM的研究和部署者在模型设计、训练及应用过程中,识别、预防和缓解这些威胁与风险,同时实现模型性能与安全及隐私保护之间的平衡.
, authors=姜毅
1, 2, 杨勇
1, 印佳丽
3, 刘小垒
4, 李吉亮
5, 王伟
6, 田有亮
7, 巫英才
1, 纪守领
1, *, authorsList=姜毅, 杨勇, 印佳丽, 刘小垒, 李吉亮, 王伟, 田有亮, 巫英才, 纪守领, authorCompany=null, correspAuthors=纪守领, authorNote=
 |
1982年生. 博士生研究生. CCF会员. 主要研究方向为数据驱动安全与隐私、人工智能安全 |
 |
1996年生. 博士生研究生. CCF会员. 主要研究方向为人工智能的安全与隐私 |
 |
1993年生. 博士,研究员,博士生导师. CCF会员. 主要研究方向为计算摄影学、深度特征融合、神经网络模型可解释性、对抗训练 |
 |
1992年生. 博士,副研究员. CCF会员. 主要研究方向为装备信息安全、人工智能安全 |
 |
1989年生. 博士,研究员,博士生导师. CCF会员. 主要研究方向为网络与信息安全、人工智能安全、大模型安全 |
 |
1976年生. 博士,教授,博士生导师. CCF杰出会员. 主要研究方向为网络与系统安全、区块链及隐私保护 |
 |
1982年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为密码学与安全协议、大数据安全、隐私保护 |
 |
1983年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为可视分析 |
 |
1986年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为数据驱动安全和隐私、人工智能安全、大数据挖掘与分析 |
, correspAuthorsNote=
, copyrightStatement=版权所有 © 2025 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=2oZl+a4fKJzatvND0bZlTw==, magXml=qzbPCFEYYpFpPLhV35J16g==, pdfUrl=null, pdf=0GkOZPmr2eMJtqh5CKqwQg==, pdfFileSize=3482746, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=JhbBJTCj9ZFzcJKblUSvMw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=VyVNhILbnChdYabLSaG2gA==, mapNumber=null, fund=null)}, authors=[Author(id=1327018638604873850, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=jiangyi2021@zju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018638680371325, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018638604873850, language=EN, stringName=Yi Jiang, firstName=Yi, middleName=null, lastName=Jiang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1College of Computer Science and Technology, Zhejiang University, Hangzhou 310007
2College of Renwu, Guizhou University, Guiyang 550025, bio={"content":"
born in 1982. PhD candidate. Member of CCF. His main research interests include data-driven security and privacy, and AI security
"}, bioImg=null, bioContent=
born in 1982. PhD candidate. Member of CCF. His main research interests include data-driven security and privacy, and AI security
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018638743285886, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018638604873850, language=CN, stringName=姜毅, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, 2, address=
1浙江大学计算机科学与技术学院 杭州 310007
2贵州大学人民武装学院 贵阳 550025, bio={"img":"RZ7ERDXTQnOYsYiB9SA5YQ==","content":"
1982年生. 博士生研究生. CCF会员. 主要研究方向为数据驱动安全与隐私、人工智能安全
"}, bioImg=RZ7ERDXTQnOYsYiB9SA5YQ==, bioContent=
1982年生. 博士生研究生. CCF会员. 主要研究方向为数据驱动安全与隐私、人工智能安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018636226703458, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, xref=1, ext=[AuthorCompanyExt(id=1327018636235092067, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636226703458, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Computer Science and Technology, Zhejiang University, Hangzhou 310007), AuthorCompanyExt(id=1327018636239286372, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636226703458, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1浙江大学计算机科学与技术学院 杭州 310007)]), AuthorCompany(id=1327018636298006629, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, xref=2, ext=[AuthorCompanyExt(id=1327018636302200934, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636298006629, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2College of Renwu, Guizhou University, Guiyang 550025), AuthorCompanyExt(id=1327018636310589543, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636298006629, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2贵州大学人民武装学院 贵阳 550025)])]), Author(id=1327018638806200448, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018638894280834, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018638806200448, language=EN, stringName=Yong Yang, firstName=Yong, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1College of Computer Science and Technology, Zhejiang University, Hangzhou 310007, bio={"content":"
born in 1996. PhD candidate. Member of CCF. His main research interest includes AI security and privacy
"}, bioImg=null, bioContent=
born in 1996. PhD candidate. Member of CCF. His main research interest includes AI security and privacy
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018638973972611, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018638806200448, language=CN, stringName=杨勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1浙江大学计算机科学与技术学院 杭州 310007, bio={"img":"SJfhEzLjgc29tggQniVKKg==","content":"
1996年生. 博士生研究生. CCF会员. 主要研究方向为人工智能的安全与隐私
"}, bioImg=SJfhEzLjgc29tggQniVKKg==, bioContent=
1996年生. 博士生研究生. CCF会员. 主要研究方向为人工智能的安全与隐私
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018636226703458, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, xref=1, ext=[AuthorCompanyExt(id=1327018636235092067, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636226703458, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Computer Science and Technology, Zhejiang University, Hangzhou 310007), AuthorCompanyExt(id=1327018636239286372, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636226703458, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1浙江大学计算机科学与技术学院 杭州 310007)])]), Author(id=1327018639083024517, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018639192076424, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018639083024517, language=EN, stringName=Jiali Yin, firstName=Jiali, middleName=null, lastName=Yin, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
3, address=
3College of Computer Science and Big Data, Fuzhou University, Fuzhou 350108, bio={"content":"
born in 1993. PhD, professor, PhD supervisor. Member of CCF. Her main research interests include computational photography, deep feature fusion interpretability of neural networks, adversarial training
"}, bioImg=null, bioContent=
born in 1993. PhD, professor, PhD supervisor. Member of CCF. Her main research interests include computational photography, deep feature fusion interpretability of neural networks, adversarial training
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018639267573898, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018639083024517, language=CN, stringName=印佳丽, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
3, address=
3福州大学计算机与大数据学院 福州 350108, bio={"img":"D9VAkKUCzex6Zas37Y1j3Q==","content":"
1993年生. 博士,研究员,博士生导师. CCF会员. 主要研究方向为计算摄影学、深度特征融合、神经网络模型可解释性、对抗训练
"}, bioImg=D9VAkKUCzex6Zas37Y1j3Q==, bioContent=
1993年生. 博士,研究员,博士生导师. CCF会员. 主要研究方向为计算摄影学、深度特征融合、神经网络模型可解释性、对抗训练
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018636369309800, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, xref=3, ext=[AuthorCompanyExt(id=1327018636377698409, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636369309800, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3College of Computer Science and Big Data, Fuzhou University, Fuzhou 350108), AuthorCompanyExt(id=1327018636503527530, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636369309800, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3福州大学计算机与大数据学院 福州 350108)])]), Author(id=1327018639343071372, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018639426957454, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018639343071372, language=EN, stringName=Xiaolei Liu, firstName=Xiaolei, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
4, address=
4Institute of Computer Application, China Academy of Engineering Physics, Mianyang, Sichuan 621054, bio={"content":"
born in 1992. PhD, associate professor. Member of CCF. His main research interests include equipment information security and AI security
"}, bioImg=null, bioContent=
born in 1992. PhD, associate professor. Member of CCF. His main research interests include equipment information security and AI security
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018639498260623, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018639343071372, language=CN, stringName=刘小垒, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
4, address=
4中国工程物理研究院计算机应用研究所 四川绵阳 621054, bio={"img":"GtZis0jI8frYCi4qHgIJiA==","content":"
1992年生. 博士,副研究员. CCF会员. 主要研究方向为装备信息安全、人工智能安全
"}, bioImg=GtZis0jI8frYCi4qHgIJiA==, bioContent=
1992年生. 博士,副研究员. CCF会员. 主要研究方向为装备信息安全、人工智能安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018638181249132, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, xref=4, ext=[AuthorCompanyExt(id=1327018638198026349, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018638181249132, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4Institute of Computer Application, China Academy of Engineering Physics, Mianyang, Sichuan 621054), AuthorCompanyExt(id=1327018638218997870, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018638181249132, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4中国工程物理研究院计算机应用研究所 四川绵阳 621054)])]), Author(id=1327018639561175186, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018639649255572, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018639561175186, language=EN, stringName=Jiliang Li, firstName=Jiliang, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
5, address=
5School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an 710049, bio={"content":"
born in 1989. PhD, professor, PhD supervisor. Member of CCF. His main research interests include network and information security, AI security, and large language model security
"}, bioImg=null, bioContent=
born in 1989. PhD, professor, PhD supervisor. Member of CCF. His main research interests include network and information security, AI security, and large language model security
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018639733141653, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018639561175186, language=CN, stringName=李吉亮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
5, address=
5西安交通大学网络空间安全学院 西安 710049, bio={"img":"kk+E8vHsPrGhgfbw+olS4w==","content":"
1989年生. 博士,研究员,博士生导师. CCF会员. 主要研究方向为网络与信息安全、人工智能安全、大模型安全
"}, bioImg=kk+E8vHsPrGhgfbw+olS4w==, bioContent=
1989年生. 博士,研究员,博士生导师. CCF会员. 主要研究方向为网络与信息安全、人工智能安全、大模型安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018638315466863, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, xref=5, ext=[AuthorCompanyExt(id=1327018638323855472, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018638315466863, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
5School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an 710049), AuthorCompanyExt(id=1327018638336438385, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018638315466863, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
5西安交通大学网络空间安全学院 西安 710049)])]), Author(id=1327018639808639127, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018639900913817, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018639808639127, language=EN, stringName=Wei Wang, firstName=Wei, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
6, address=
6Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100091, bio={"content":"
born in 1976. PhD, professor, PhD supervisor. Distinguished member of CCF. His main research interests include cyberspace and system security, and blockchain and privacy preservation
"}, bioImg=null, bioContent=
born in 1976. PhD, professor, PhD supervisor. Distinguished member of CCF. His main research interests include cyberspace and system security, and blockchain and privacy preservation
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018639972216986, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018639808639127, language=CN, stringName=王伟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
6, address=
6智能交通数据安全与隐私保护技术北京市重点实验室(北京交通大学) 北京 100091, bio={"img":"QYKmacuzZ6x1mosU3M0S5w==","content":"
1976年生. 博士,教授,博士生导师. CCF杰出会员. 主要研究方向为网络与系统安全、区块链及隐私保护
"}, bioImg=QYKmacuzZ6x1mosU3M0S5w==, bioContent=
1976年生. 博士,教授,博士生导师. CCF杰出会员. 主要研究方向为网络与系统安全、区块链及隐私保护
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018638411935858, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, xref=6, ext=[AuthorCompanyExt(id=1327018638420324467, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018638411935858, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
6Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100091), AuthorCompanyExt(id=1327018638428713076, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018638411935858, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
6智能交通数据安全与隐私保护技术北京市重点实验室(北京交通大学) 北京 100091)])]), Author(id=1327018640047714460, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018640127406238, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018640047714460, language=EN, stringName=Youliang Tian, firstName=Youliang, middleName=null, lastName=Tian, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
7, address=
7College of Computer Science and Technology, Guizhou University, Guiyang 550025, bio={"content":"
born in 1982. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include cryptography and security protocols, big data security, and privacy protection
"}, bioImg=null, bioContent=
born in 1982. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include cryptography and security protocols, big data security, and privacy protection
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018640198709407, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018640047714460, language=CN, stringName=田有亮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
7, address=
7贵州大学计算机科学与技术学院 贵阳 550025, bio={"img":"mA8C1+/5vvbIK7ogiQTFtA==","content":"
1982年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为密码学与安全协议、大数据安全、隐私保护
"}, bioImg=mA8C1+/5vvbIK7ogiQTFtA==, bioContent=
1982年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为密码学与安全协议、大数据安全、隐私保护
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018638516793462, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, xref=7, ext=[AuthorCompanyExt(id=1327018638525182071, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018638516793462, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
7College of Computer Science and Technology, Guizhou University, Guiyang 550025), AuthorCompanyExt(id=1327018638533570680, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018638516793462, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
7贵州大学计算机科学与技术学院 贵阳 550025)])]), Author(id=1327018640253235361, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, orderNo=7, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018640320344227, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018640253235361, language=EN, stringName=Yingcai Wu, firstName=Yingcai, middleName=null, lastName=Wu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1College of Computer Science and Technology, Zhejiang University, Hangzhou 310007, bio={"content":"
born in 1983. PhD, professor, PhD supervisor. Senior member of CCF. His main research interest includes visual analytics
"}, bioImg=null, bioContent=
born in 1983. PhD, professor, PhD supervisor. Senior member of CCF. His main research interest includes visual analytics
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018640383258788, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018640253235361, language=CN, stringName=巫英才, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1浙江大学计算机科学与技术学院 杭州 310007, bio={"img":"hAbSuRu2pwDOTyd3BW7F2Q==","content":"
1983年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为可视分析
"}, bioImg=hAbSuRu2pwDOTyd3BW7F2Q==, bioContent=
1983年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为可视分析
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018636226703458, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, xref=1, ext=[AuthorCompanyExt(id=1327018636235092067, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636226703458, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Computer Science and Technology, Zhejiang University, Hangzhou 310007), AuthorCompanyExt(id=1327018636239286372, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636226703458, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1浙江大学计算机科学与技术学院 杭州 310007)])]), Author(id=1327018640437784742, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, orderNo=8, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=sji@zju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1327018640513282216, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018640437784742, language=EN, stringName=Shouling Ji, firstName=Shouling, middleName=null, lastName=Ji, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, *, address=
1College of Computer Science and Technology, Zhejiang University, Hangzhou 310007, bio={"content":"
born in 1986. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include data-driven security and privacy, AI security, and big data mining and analytics
"}, bioImg=null, bioContent=
born in 1986. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include data-driven security and privacy, AI security, and big data mining and analytics
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018640576196777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, authorId=1327018640437784742, language=CN, stringName=纪守领, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, *, address=
1浙江大学计算机科学与技术学院 杭州 310007, bio={"img":"ogMOx4x4FhrBbjhHlY1PIQ==","content":"
1986年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为数据驱动安全和隐私、人工智能安全、大数据挖掘与分析
"}, bioImg=ogMOx4x4FhrBbjhHlY1PIQ==, bioContent=
1986年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为数据驱动安全和隐私、人工智能安全、大数据挖掘与分析
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018636226703458, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, xref=1, ext=[AuthorCompanyExt(id=1327018636235092067, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636226703458, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Computer Science and Technology, Zhejiang University, Hangzhou 310007), AuthorCompanyExt(id=1327018636239286372, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636226703458, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1浙江大学计算机科学与技术学院 杭州 310007)])])], keywords=[Keyword(id=1327018640664277162, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, orderNo=1, keyword=large language models (LLMs)), Keyword(id=1327018640743968939, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, orderNo=2, keyword=pre-trained language models), Keyword(id=1327018640806883500, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, orderNo=3, keyword=security), Keyword(id=1327018640869798061, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, orderNo=4, keyword=privacy), Keyword(id=1327018640932712622, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, orderNo=5, keyword=threat), Keyword(id=1327018641033375919, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, orderNo=1, keyword=大语言模型), Keyword(id=1327018642681737392, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, orderNo=2, keyword=预训练语言模型), Keyword(id=1327018642769817777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, orderNo=3, keyword=安全), Keyword(id=1327018642836926642, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, orderNo=4, keyword=隐私), Keyword(id=1327018642912424115, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, orderNo=5, keyword=威胁)], refs=[Reference(id=1327018645470949586, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[J]. arXiv preprint, arXiv: 1706.03762, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018645546447059, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Radford A, Narasimhan K, Salimans T, et al. Improving language understanding by generative pre-training[EB/OL]. 2018[2024-05-23]. https://hayate-lab.com/wp-content/uploads/2023/05/43372bfa750340059ad87ac8e538c53b.pdf, articleTitle=null, refAbstract=null), Reference(id=1327018647199002836, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Devlin J, Chang M W, Lee K, et al. BERT: Pre-training of deep bidirectional Transformers for language understanding[J]. arXiv preprint, arXiv: 1810.04805, 2019, articleTitle=null, refAbstract=null), Reference(id=1327018647274500309, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Mikolov T, Chen K, Corrado G, et al. Efficient estimation of word representations in vector space[J]. arXiv preprint, arXiv: 1301.3781, 2013, articleTitle=null, refAbstract=null), Reference(id=1327018647345803478, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=Pennington J, Socher R, Manning C. GloVe: Global vectors for word representation[C]//Proc of the 19th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2014: 1532−1543, articleTitle=null, refAbstract=null), Reference(id=1327018647408718039, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=陈慧敏,刘知远,孙茂松. 大语言模型时代的社会机遇与挑战[J]. 计算机研究与发展,2024,61(5):1094−1103, articleTitle=null, refAbstract=null), Reference(id=1327018647475826904, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Huimin, Liu Zhiyuan, Sun Maosong. The social opportunities and challenges in the era of large language models[J]. Journal of Computer Research and Development, 2024, 61(5): 1094−1103 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327018647538741465, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Brown T B, Mann B, Ryder N, et al. Language models are few-shot learners[J]. arXiv preprint, arXiv: 2005.14165, 2020, articleTitle=null, refAbstract=null), Reference(id=1327018647622627546, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Morris J X, Lifland E, Yoo J Y, et al. TextAttack: A framework for adversarial attacks, data augmentation, and adversarial training in NLP[J]. arXiv preprint, arXiv: 2005.05909, 2020, articleTitle=null, refAbstract=null), Reference(id=1327018647714902235, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Zeng Guoyang, Qi Fanchao, Zhou Qianrui, et al. OpenAttack: An open-source textual adversarial attack toolkit[C]//Proc of the 59th Annual Meeting of the ACL and the 11th Int Joint Conf on Natural Language Processing: System Demonstrations. Stroudsburg, PA: ACL, 2021: 363−371, articleTitle=null, refAbstract=null), Reference(id=1327018647777816796, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Boxin, Xu Chejian, Wang Shuohang, et al. Adversarial GLUE: A multi-task benchmark for robustness evaluation of language models[J]. arXiv preprint, arXiv: 2111.02840, 2021, articleTitle=null, refAbstract=null), Reference(id=1327018647857508573, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Papernot N, McDaniel P, Swami A, et al. Crafting adversarial input sequences for recurrent neural networks[C]//Proc of the 2016 IEEE Military Communications Conf. Piscataway, NJ: IEEE, 2016: 49−54, articleTitle=null, refAbstract=null), Reference(id=1327018647912034526, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Liang Bin, Li Hongcheng, Su Miaoqiang, et al. Deep text classification can be fooled[C]//Proc of the 27th Int Joint Conf on Artificial Intelligence. Palo Alto, CA: International Joint Conference on Artificial Intelligence Organization, 2018: 4208−4215, articleTitle=null, refAbstract=null), Reference(id=1327018647983337695, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Ebrahimi J, Rao A, Lowd D, et al. HotFlip: White-box adversarial examples for text classification[J]. arXiv preprint, arXiv: 1712.06751, 2018, articleTitle=null, refAbstract=null), Reference(id=1327018648042057952, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Jinfeng, Ji Shouling, Du Tianyu, et al. TextBugger: Generating adversarial text against real-world applications[J]. arXiv preprint, arXiv: 1812.05271, 2018, articleTitle=null, refAbstract=null), Reference(id=1327018648100778209, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Behjati M, Moosavi-Dezfooli S M, Baghshah M S, et al. Universal adversarial attacks on text classifiers[C]//Proc of the 44th IEEE Int Conf on Acoustics, Speech and Signal Processing (ICASSP). Piscataway, NJ: IEEE, 2019: 7345−7349, articleTitle=null, refAbstract=null), Reference(id=1327018648172081378, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Wallace E, Feng S, Kandpal N, et al. Universal adversarial triggers for attacking and analyzing NLP[J]. arXiv preprint, arXiv: 1908.07125, 2021, articleTitle=null, refAbstract=null), Reference(id=1327018648247578851, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Gao J, Lanchantin J, Soffa M L, et al. Black-box generation of adversarial text sequences to evade deep learning classifiers[J]. arXiv preprint, arXiv: 1801.04354, 2018, articleTitle=null, refAbstract=null), Reference(id=1327018648302104804, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Eger S, Şahin G G, Rücklé A, et al. Text processing like humans do: Visually attacking and shielding NLP systems[C]//Proc of the 18th Conf of the North American Chapter of the ACL: Human Language Technologies (Volume 1: Long and Short Papers). Stroudsburg, PA: ACL, 2019: 1634−1647, articleTitle=null, refAbstract=null), Reference(id=1327018648356630757, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Jin Di, Jin Zhijing, Zhou J, et al. Is BERT really robust? A strong baseline for natural language attack on text classification and entailment[J]. arXiv preprint, arXiv: 1907.11932, 2020, articleTitle=null, refAbstract=null), Reference(id=1327018648423739622, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Linyang, Ma Ruotian, Guo Qipeng, et al. BERT-Attack: Adversarial attack against BERT using BERT[J]. arXiv preprint, arXiv: 2004.09984, 2020, articleTitle=null, refAbstract=null), Reference(id=1327018648482459879, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Garg S, Ramakrishnan G. BAE: BERT-based adversarial examples for text classification[C]//Proc of the 25th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2020: 6174−6181, articleTitle=null, refAbstract=null), Reference(id=1327018648549568744, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Dianqi, Zhang Yizhe, Peng Hao, et al. Contextualized perturbation for textual adversarial attack[J]. arXiv preprint, arXiv: 2009.07502, 2021, articleTitle=null, refAbstract=null), Reference(id=1327018648616677609, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Maheshwary R, Maheshwary S, Pudi V. Generating natural language attacks in a hard label black box setting[C]//Proc of the 35th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2021: 13525−13533, articleTitle=null, refAbstract=null), Reference(id=1327018648675397866, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Ye Muchao, Miao Chenglin, Wang Ting, et al. TextHoaxer: Budgeted hard-label adversarial attacks on text[C]//Proc of the 36th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2022: 3877−3884, articleTitle=null, refAbstract=null), Reference(id=1327018648742506731, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Lei, Chen Yangyi, Cui Ganqu, et al. Exploring the universal vulnerability of prompt-based learning paradigm[J]. arXiv preprint, arXiv: 2204.05239, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018648809615596, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Lei, Chen Yangyi, Cui Ganqu, et al. A prompting-based approach for adversarial example generation and robustness enhancement[J]. arXiv preprint, arXiv: 2203.10714, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018648868335853, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Xiao, Zheng Yanan, Du Zhengxiao, et al. GPT understands, too[J]. AI Open, 2024, 5: 208−215, articleTitle=null, refAbstract=null), Reference(id=1327018648943833326, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Xiao,Zheng Yanan,Du Zhengxiao,et al. GPT understands,too[J]. AI Open,2024,5:208−215, articleTitle=null, refAbstract=null), Reference(id=1327018649031913711, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Lu Yao, Bartolo M, Moore A, et al. Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity[J]. arXiv preprint, arXiv: 2104.08786, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018649132577008, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Jiongxiao, Liu Zichen, Park K H, et al. Adversarial demonstration attacks on large language models[J]. arXiv preprint, arXiv: 2305.14950, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018649191297265, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Qiang Yao, Zhou Xiangyu, Zhu Dongxiao. Hijacking large language models via adversarial in-context learning[J]. arXiv preprint, arXiv: 2311.09948, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018649258406130, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Shin T, Razeghi Y, Logan IV R L, et al. AutoPrompt: Eliciting knowledge from language models with automatically generated prompts[C]//Proc of the 25th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2020: 4222−4235, articleTitle=null, refAbstract=null), Reference(id=1327018649317126387, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Shi Yundi, Li Piji, Yin Changchun, et al. PromptAttack: Prompt-based attack for language models via gradient search[J]. arXiv preprint, arXiv: 2209.01882, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018649384235252, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=李南,丁益东,江浩宇,等. 面向大语言模型的越狱攻击综述[J]. 计算机研究与发展,2024,61(5):1156−1181, articleTitle=null, refAbstract=null), Reference(id=1327018649455538421, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Nan, Ding Yidong, Jiang Haoyu, et al. Jailbreak attack for large language models: A survey[J]. Journal of Computer Research and Development, 2024, 61(5): 1156−1181 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327018649522647286, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Perez F, Ribeiro I. Ignore previous prompt: Attack techniques for language models[J]. arXiv preprint, arXiv: 2211.09527, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018649585561847, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Shen Xinyue, Chen Zeyuan, Backes M, et al. “Do anything now”: Characterizing and evaluating in-the-wild jailbreak prompts on large language models[J]. arXiv preprint, arXiv: 2308.03825, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018649652670712, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Gu Xiangming, Zheng Xiaosen, Pang Tianyu, et al. Agent Smith: A single image can jailbreak one million multimodal LLM agents exponentially fast[J]. arXiv preprint, arXiv: 2402.08567, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018649707196665, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhan Qiusi, Liang Zhixiang, Ying Zifan, et al. InjecAgent: Benchmarking indirect prompt injections in tool-integrated large language model agents[J]. arXiv preprint arXiv: 2403.02691, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018649765916922, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Wei A, Haghtalab N, Steinhardt J. Jailbroken: How does LLM safety training fail?[J]. arXiv preprint, arXiv: 2307.02483, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018649837220091, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Yi, Deng Gelei, Li Yuekang, et al. Prompt injection attack against LLM-integrated applications[J]. arXiv preprint, arXiv: 2306.05499, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018649921106172, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Abdelnabi S, Greshake K, Mishra S, et al. Not what you’ve signed up for: Compromising real-world LLM-integrated applications with indirect prompt injection[C]//Proc of the 16th ACM Workshop on Artificial Intelligence and Security. New York: ACM, 2023: 79−90, articleTitle=null, refAbstract=null), Reference(id=1327018649988215037, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Zou A, Wang Zifan, Kolter J Z, et al. Universal and transferable adversarial attacks on aligned language models[J]. arXiv preprint, arXiv: 2307.15043, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018651737239806, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Sicheng, Zhang Ruiyi, An Bang, et al. AutoDAN: Interpretable gradient-based adversarial attacks on large language models[J]. arXiv preprint, arXiv: 2310.15140, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018651850486015, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Dai Jiazhu, Chen Chuanshuai, Li Yufeng. A backdoor attack against LSTM-based text classification systems[J]. IEEE Access, 2019, 7: 138872−138878, articleTitle=null, refAbstract=null), Reference(id=1327018651913400576, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Wenkai, Lin Yankai, Li Peng, et al. Rethinking stealthiness of backdoor attack against NLP models[C]//Proc of the 59th Annual Meeting of the ACL and the 11th Int Joint Conf on Natural Language Processing (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2021: 5543−5557, articleTitle=null, refAbstract=null), Reference(id=1327018651988898049, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Kwon H, Lee S. Textual backdoor attack for the text classification system[J]. Security and Communication Networks, 2021, 2021(1): 1−11, articleTitle=null, refAbstract=null), Reference(id=1327018652056006914, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Kurita K, Michel P, Neubig G. Weight poisoning attacks on pre-trained models[J]. arXiv preprint, arXiv: 2004.06660, 2020, articleTitle=null, refAbstract=null), Reference(id=1327018652127310083, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Xiaoyi, Salem A, Chen Dingfan, et al. BadNL: Backdoor attacks against NLP models with semantic-preserving improvements[C]//Proc of the 37th Annual Computer Security Applications Conf. New York: ACM, 2021: 554−569, articleTitle=null, refAbstract=null), Reference(id=1327018652198613252, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Lu Hengyang, Fan Chenyou, Yang Jun, et al. Where to attack: A dynamic locator model for backdoor attack in text classifications[C]//Proc of the 29th Int Conf on Computational Linguistics. Gyeongju, Republic of Korea: International Committee on Computational Linguistics, 2022: 984−993, articleTitle=null, refAbstract=null), Reference(id=1327018652261527813, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Qi Fanchao, Li Mukai, Chen Yangyi, et al. Hidden Killer: Invisible textual backdoor attacks with syntactic trigger[J]. arXiv preprint, arXiv: 2105.12400, 2021, articleTitle=null, refAbstract=null), Reference(id=1327018652320248070, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Qi Fanchao, Chen Yangyi, Zhang Xurui, et al. Mind the style of text! adversarial and backdoor attacks based on text style transfer[J]. arXiv preprint, arXiv: 2110.07139, 2021, articleTitle=null, refAbstract=null), Reference(id=1327018652383162631, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Pan Xudong, Zhang Mi, Sheng Beina, et al. Hidden trigger backdoor attack on NLP models via linguistic style manipulation[C]//Proc of the 31st USENIX Security Symp (USENIX Security 22). Berkeley, CA: USENIX Association, 2022: 3611−3628, articleTitle=null, refAbstract=null), Reference(id=1327018652450271496, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Kirkpatrick J, Pascanu R, Rabinowitz N, et al. Overcoming catastrophic forgetting in neural networks[J]. Proceedings of the National Academy of Sciences, 2017, 114(13): 3521−3526, articleTitle=null, refAbstract=null), Reference(id=1327018652517380361, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Linyang, Song Demin, Li Xiaonan, et al. Backdoor attacks on pre-trained models by layerwise weight poisoning[J]. arXiv preprint, arXiv: 2108.13888, 2021, articleTitle=null, refAbstract=null), Reference(id=1327018652597072138, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Wenkai, Li Lei, Zhang Zhiyuan, et al. Be careful about poisoned word embeddings: Exploring the vulnerability of the embedding layers in NLP models[J]. arXiv preprint, arXiv: 2103.15543, 2021, articleTitle=null, refAbstract=null), Reference(id=1327018652659986699, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=55, rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=Merity S, Xiong C, Bradbury J, et al. Pointer sentinel mixture models[J]. arXiv preprint, arXiv: 1609.07843, 2016, articleTitle=null, refAbstract=null), Reference(id=1327018652718706956, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=56, rfOrder=58, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Xinyang, Zhang Zheng, Ji Shouling, et al. Trojaning language models for fun and profit[C]//Proc of the 6th IEEE European Symp on Security and Privacy (EuroS&P). Piscataway, NJ: IEEE, 2021: 179−197, articleTitle=null, refAbstract=null), Reference(id=1327018652790010125, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=57, rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Kangjie, Meng Yuxian, Sun Xiaofei, et al. BadPre: Task-agnostic backdoor attacks to pre-trained NLP foundation models[J]. arXiv preprint, arXiv: 2110.02467, 2021, articleTitle=null, refAbstract=null), Reference(id=1327018652857118990, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=58, rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=Shen Lujia, Ji Shouling, Zhang Xuhong, et al. Backdoor pre-trained models can transfer to all[C]//Proc of the 28th ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2021: 3141−3158, articleTitle=null, refAbstract=null), Reference(id=1327018652915839247, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=59, rfOrder=61, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Zhengyan, Xiao Guangxuan, Li Yongwei, et al. Red alarm for pre-trained models: Universal vulnerability to neuron-level backdoor attacks[J]. Machine Intelligence Research, 2023, 20(2): 180−193, articleTitle=null, refAbstract=null), Reference(id=1327018652987142416, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=60, rfOrder=62, authorNames=null, journalName=null, refType=null, unstructuredReference=Du Wei, Li Peixuan, Li Boqun, et al. UOR: Universal backdoor attacks on pre-trained language models[J]. arXiv preprint, arXiv: 2305.09574, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018653045862673, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=61, rfOrder=63, authorNames=null, journalName=null, refType=null, unstructuredReference=Du Wei, Zhao Yichun, Li Boqun, et al. PPT: Backdoor attacks on pre-trained models via poisoned prompt tuning[C]//Proc of the 31st Int Joint Conf on Artificial Intelligence. Palo Alto, CA: International Joint Conference on Artificial Intelligence Organization, 2022: 680−686, articleTitle=null, refAbstract=null), Reference(id=1327018653104582930, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=62, rfOrder=64, authorNames=null, journalName=null, refType=null, unstructuredReference=Cai Xiangrui, Xu Haidong, Xu Sihan, et al. BadPrompt: Backdoor attacks on continuous prompts[J]. arXiv preprint, arXiv: 2211.14719, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018653159108883, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=63, rfOrder=65, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Shuai, Wen Jinming, Tuan L A, et al. Prompt as triggers for backdoor attack: Examining the vulnerability in language models[C]//Proc of the 28th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2023: 12303−12317, articleTitle=null, refAbstract=null), Reference(id=1327018653217829140, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=64, rfOrder=66, authorNames=null, journalName=null, refType=null, unstructuredReference=Mei Kai, Li Zheng, Wang Zhenting, et al. NOTABLE: Transferable backdoor attacks against prompt-based NLP models[J]. arXiv preprint, arXiv: 2305.17826, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018653280743701, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=65, rfOrder=67, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Jiashu, Ma M D, Wang Fei, et al. Instructions as backdoors: Backdoor vulnerabilities of instruction tuning for large language models[J]. arXiv preprint, arXiv: 2305.14710, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018653356241174, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=66, rfOrder=68, authorNames=null, journalName=null, refType=null, unstructuredReference=Yan Jun, Yadav V, Li Shiyang, et al. Backdooring instruction-tuned large language models with virtual prompt injection[J]. arXiv preprint, arXiv: 2307.16888, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018653427544343, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=67, rfOrder=69, authorNames=null, journalName=null, refType=null, unstructuredReference=Rando J, Tramèr F. Universal jailbreak backdoors from poisoned human feedback[J]. arXiv preprint, arXiv: 2311.14455, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018653524013336, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=68, rfOrder=70, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Wenkai, Bi Xiaohan, Lin Yankai, et al. Watch out for your agents! Investigating backdoor threats to LLM-based agents[J]. arXiv preprint, arXiv: 2402.11208, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018653616288025, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=69, rfOrder=71, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Yifei, Xue Dizhan, Zhang Shengjie, et al. BadAgent: Inserting and activating backdoor attacks in LLM agents[J]. arXiv preprint, arXiv: 2406.03007, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018653679202586, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=70, rfOrder=72, authorNames=null, journalName=null, refType=null, unstructuredReference=Yao Yunzhi, Wang Peng, Tian Bozhong, et al. Editing large language models: Problems, methods, and opportunities[C]//Proc of the 28th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2023: 10222−10240, articleTitle=null, refAbstract=null), Reference(id=1327018653746311451, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=71, rfOrder=73, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Ningyu, Yao Yunzhi, Tian Bozhong, et al. A comprehensive study of knowledge editing for large language models[J]. arXiv preprint, arXiv: 2401.01286, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018653830197532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=72, rfOrder=74, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Yanzhou, Li Tianlin, Chen Kangjie, et al. BadEdit: Backdooring large language models by model editing[J]. arXiv preprint, arXiv: 2403.13355, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018653905695005, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=73, rfOrder=75, authorNames=null, journalName=null, refType=null, unstructuredReference=Qiu Jiyang, Ma Xinbei, Zhang Zhuosheng, et al. MEGen: Generative backdoor in large language models via model editing[J]. arXiv preprint, arXiv: 2408.10722, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018653976998174, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=74, rfOrder=76, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Hao, Guo Shangwei, He Jialing, et al. EvilEdit: Backdooring text-to-image diffusion models in one second[C]//Proc of the 32nd ACM Int Conf on Multimedia. New York: ACM, 2024: 3657−3665, articleTitle=null, refAbstract=null), Reference(id=1327018654048301343, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=75, rfOrder=77, authorNames=null, journalName=null, refType=null, unstructuredReference=Barreno M, Nelson B, Sears R, et al. Can machine learning be secure?[C]//Proc of the 1st ACM Symp on Information, Computer and Communications Security. New York: ACM, 2006: 16−25, articleTitle=null, refAbstract=null), Reference(id=1327018654111215904, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=76, rfOrder=78, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Gang, Wang Tianyi, Zheng Haitao, et al. Man vs. machine: Practical adversarial detection of malicious crowdsourcing workers[C]//Proc of the 23rd USENIX Security Symp (USENIX Security 2014). Berkeley, CA: USENIX Association, 2014: 239−254, articleTitle=null, refAbstract=null), Reference(id=1327018654190907681, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=77, rfOrder=79, authorNames=null, journalName=null, refType=null, unstructuredReference=Miao Chenglin, Li Qi, Xiao Houping, et al. Towards data poisoning attacks in crowd sensing systems[C]//Proc of the 18th ACM Int Symp on Mobile Ad Hoc Networking and Computing. New York: ACM, 2018: 111−120, articleTitle=null, refAbstract=null), Reference(id=1327018654270599458, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=78, rfOrder=80, authorNames=null, journalName=null, refType=null, unstructuredReference=Feng Ji, Cai Qizhi, Zhou Zhihua. Learning to confuse: Generating training time adversarial data with auto-encoder[J]. arXiv preprint, arXiv: 1905.09027, 2019, articleTitle=null, refAbstract=null), Reference(id=1327018654404817187, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=79, rfOrder=81, authorNames=null, journalName=null, refType=null, unstructuredReference=Shafahi A, Huang W R, Najibi M, et al. Poison frogs! Targeted clean-label poisoning attacks on neural networks[J]. arXiv preprint, arXiv: 1804.00792, 2018, articleTitle=null, refAbstract=null), Reference(id=1327018654471926052, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=80, rfOrder=82, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Chen, Huang W R, Li Hengduo, et al. Transferable clean-label poisoning attacks on deep neural nets[C]//Proc of the 36th Int Conf on Machine Learning. New York: PMLR, 2019: 7614−7623, articleTitle=null, refAbstract=null), Reference(id=1327018654543229221, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=81, rfOrder=83, authorNames=null, journalName=null, refType=null, unstructuredReference=Wallace E, Zhao T Z, Feng S, et al. Concealed data poisoning attacks on NLP Models[J]. arXiv preprint, arXiv: 2010.12563, 2020, articleTitle=null, refAbstract=null), Reference(id=1327018656187396390, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=82, rfOrder=84, authorNames=null, journalName=null, refType=null, unstructuredReference=Jagielski M, Severi G, Pousette Harger N, et al. Subpopulation data poisoning attacks[C]//Proc of the 28th ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2021: 3104−3122, articleTitle=null, refAbstract=null), Reference(id=1327018656254505255, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=83, rfOrder=85, authorNames=null, journalName=null, refType=null, unstructuredReference=Schuster R, Song C, Tromer E, et al. You autocomplete me: Poisoning vulnerabilities in neural code completion[C]//Proc of the 30th USENIX Security Symp (USENIX Security 21). Berkeley, CA: USENIX Association, 2021: 1559−1575, articleTitle=null, refAbstract=null), Reference(id=1327018656325808424, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=84, rfOrder=86, authorNames=null, journalName=null, refType=null, unstructuredReference=He Pengfei, Xu Han, Xing Yue, et al. Data poisoning for in-context learning[J]. arXiv preprint, arXiv: 2402.02160, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018656409694505, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=85, rfOrder=87, authorNames=null, journalName=null, refType=null, unstructuredReference=Hendel R, Geva M, Globerson A. In-context learning creates task vectors[C]//Proc of the 28th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2023: 9318−9333, articleTitle=null, refAbstract=null), Reference(id=1327018656493580586, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=86, rfOrder=88, authorNames=null, journalName=null, refType=null, unstructuredReference=Peng Baolin, Li Chunyuan, He Pengcheng, et al. Instruction tuning with GPT−4[J]. arXiv preprint, arXiv: 2304.03277, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018656573272363, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=87, rfOrder=89, authorNames=null, journalName=null, refType=null, unstructuredReference=Shu Manli, Wang Jiongxiao, Zhu Chen, et al. On the exploitability of instruction tuning[J]. arXiv preprint, arXiv: 2306.17194, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018656644575532, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=88, rfOrder=90, authorNames=null, journalName=null, refType=null, unstructuredReference=Wan A, Wallace E, Shen S, et al. Poisoning language models during instruction tuning[J]. arXiv preprint, arXiv: 2305.00944, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018656715878701, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=89, rfOrder=91, authorNames=null, journalName=null, refType=null, unstructuredReference=Qiang Yao, Zhou Xiangyu, Zade S Z, et al. Learning to poison large language models during instruction tuning[J]. arXiv preprint, arXiv: 2402.13459, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018656791376174, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=90, rfOrder=92, authorNames=null, journalName=null, refType=null, unstructuredReference=Zou Wei, Geng Runpeng, Wang Binghui, et al. PoisonedRAG: Knowledge poisoning attacks to retrieval-augmented generation of large language models[J]. arXiv preprint, arXiv: 2402.07867, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018656887845167, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=91, rfOrder=93, authorNames=null, journalName=null, refType=null, unstructuredReference=Touvron H, Martin L, Stone K, et al. LLama 2: Open foundation and fine-tuned chat models[J]. arXiv preprint, arXiv: 2307.09288, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018656971731248, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=92, rfOrder=94, authorNames=null, journalName=null, refType=null, unstructuredReference=陈炫婷,叶俊杰,祖璨,等. GPT系列大语言模型在自然语言处理任务中的鲁棒性[J]. 计算机研究与发展,2024,61(5):1128−1142, articleTitle=null, refAbstract=null), Reference(id=1327018657038840113, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=92, rfOrder=95, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Xuanting, Ye Junjie, Zu Can. Robustness of GPT large language models on natural language processing tasks[J]. Journal of Computer Research and Development, 2024, 61(5): 1128−1142 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327018657110143282, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=93, rfOrder=96, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Lei, Yu Weijiang, Ma Weitao, et al. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions[J]. arXiv preprint, arXiv: 2311.05232, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018657202417971, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=94, rfOrder=97, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin S, Hilton J, Evans O. TruthfulQA: Measuring how models mimic human falsehoods[J]. arXiv preprint, arXiv: 2109.07958, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018657332441396, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=95, rfOrder=98, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee K, Ippolito D, Nystrom A, et al. Deduplicating training data makes language models better[J]. arXiv preprint, arXiv: 2107.06499, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018657395355957, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=96, rfOrder=99, authorNames=null, journalName=null, refType=null, unstructuredReference=Yu Fangyi, Quartey L, Schilder F. Legal prompting: Teaching a language model to think like a lawyer[J]. arXiv preprint, arXiv: 2212.01326, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018657449881910, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=97, rfOrder=100, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Yunxiang, Li Zihan, Zhang Kai, et al. ChatDoctor: A medical chat model fine-tuned on a large language model meta-AI (LLaMA) using medical domain knowledge[J]. arXiv preprint, arXiv: 2303.14070, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018657512796471, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=98, rfOrder=101, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Zuchao, Zhang Shitou, Zhao Hai, et al. BatGPT: A bidirectional autoregessive talker from generative pre-trained transformer[J]. arXiv preprint, arXiv: 2307.00360, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018657579905336, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=99, rfOrder=102, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Chaojun, Sennrich R. On exposure bias, hallucination and domain shift in neural machine translation[C]//Proc of the 58th Annual Meeting of the ACL. Stroudsburg, PA: ACL, 2020: 3544−3552, articleTitle=null, refAbstract=null), Reference(id=1327018657672180025, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=100, rfOrder=103, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Muru, Press O, Merrill W, et al. How language model hallucinations can snowball[J]. arXiv preprint, arXiv: 2305.13534, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018657743483194, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=101, rfOrder=104, authorNames=null, journalName=null, refType=null, unstructuredReference=Perez E, Ringer S, Lukošiūtė K, et al. Discovering language model behaviors with model-written evaluations[J]. arXiv preprint, arXiv: 2212.09251, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018657798009147, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=102, rfOrder=105, authorNames=null, journalName=null, refType=null, unstructuredReference=Cheng Qinyuan, Sun Tianxiang, Zhang Wenwei, et al. Evaluating hallucinations in Chinese large language models[J]. arXiv preprint, arXiv: 2310.03368, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018657865118012, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=103, rfOrder=106, authorNames=null, journalName=null, refType=null, unstructuredReference=Chuang Y S, Xie Yujia, Luo Hongyin, et al. DoLa: Decoding by contrasting layers improves factuality in large language models[J]. arXiv preprint, arXiv: 2309.03883, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018657923838269, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=104, rfOrder=107, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu N F, Lin K, Hewitt J, et al. Lost in the middle: How language models use long contexts[J]. arXiv preprint, arXiv: 2307.03172, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018657978364222, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=105, rfOrder=108, authorNames=null, journalName=null, refType=null, unstructuredReference=Shi Weijia, Han Xiaochuang, Lewis M, et al. Trusting your evidence: Hallucinate less with context-aware decoding[J]. arXiv preprint, arXiv: 2305.14739, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018658053861695, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=106, rfOrder=109, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Yifei, Lin Zeqi, Zhang Shizhuo, et al. Making large language models better reasoners with step-aware verifier[J]. arXiv preprint, arXiv: 2206.02336, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018658146136384, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=107, rfOrder=110, authorNames=null, journalName=null, refType=null, unstructuredReference=Weng Yixuan, Zhu Minjun, Xia Fei, et al. Large language models are better reasoners with self-verification[J]. arXiv preprint, arXiv: 2212.09561, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018658209050945, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=108, rfOrder=111, authorNames=null, journalName=null, refType=null, unstructuredReference=Stechly K, Marquez M, Kambhampati S. GPT−4 doesn’t know it’s wrong: An analysis of iterative prompting for reasoning problems[J]. arXiv preprint, arXiv: 2310.12397, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018658326491458, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=109, rfOrder=112, authorNames=null, journalName=null, refType=null, unstructuredReference=El-Mhamdi E M, Farhadkhani S, Guerraoui R, et al. On the impossible safety of large AI models[J]. arXiv preprint, arXiv: 2209.15259, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018658397794627, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=110, rfOrder=113, authorNames=null, journalName=null, refType=null, unstructuredReference=Gehman S, Gururangan S, Sap M, et al. RealToxicityPrompts: Evaluating neural toxic degeneration in language models[J]. arXiv preprint, arXiv: 2009.11462, 2020, articleTitle=null, refAbstract=null), Reference(id=1327018658473292100, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=111, rfOrder=114, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Boxin, Chen Weixin, Pei Hengzhi, et al. DecodingTrust: A comprehensive assessment of trustworthiness in GPT models[J]. arXiv preprint, arXiv: 2306.11698, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018658594926917, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=112, rfOrder=115, authorNames=null, journalName=null, refType=null, unstructuredReference=Urchs S, Thurner V, Aßenmacher M, et al. How prevalent is gender bias in ChatGPT? Exploring German and English ChatGPT responses[J]. arXiv preprint, arXiv: 2310.03031, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018658678812998, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=113, rfOrder=116, authorNames=null, journalName=null, refType=null, unstructuredReference=Nozza D, Bianchi F, Hovy D. HONEST: Measuring hurtful sentence completion in language models[C]//Proc of the 19th Conf of the North American Chapter of the ACL: Human Language Technologies. Stroudsburg, PA: ACL, 2021: 2398−2406, articleTitle=null, refAbstract=null), Reference(id=1327018658922082631, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=114, rfOrder=117, authorNames=null, journalName=null, refType=null, unstructuredReference=Nadeem M, Bethke A, Reddy S. StereoSet: Measuring stereotypical bias in pretrained language models[J]. arXiv preprint, arXiv: 2004.09456, 2020, articleTitle=null, refAbstract=null), Reference(id=1327018659022745928, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=115, rfOrder=118, authorNames=null, journalName=null, refType=null, unstructuredReference=Lucy L, Bamman D. Gender and representation bias in GPT−3 generated stories[C]//Proc of the 3rd Workshop on Narrative Understanding. Stroudsburg, PA: ACL, 2021: 48−55, articleTitle=null, refAbstract=null), Reference(id=1327018660671107401, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=116, rfOrder=119, authorNames=null, journalName=null, refType=null, unstructuredReference=Abid A, Farooqi M, Zou J. Persistent anti-Muslim bias in large language models[C]//Proc of the 2021 AAAI/ACM Conf on AI, Ethics, and Society. New York: ACM, 2021: 298−306, articleTitle=null, refAbstract=null), Reference(id=1327018660746604874, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=117, rfOrder=120, authorNames=null, journalName=null, refType=null, unstructuredReference=Patel R, Pavlick E. Was it “stated” or was it “claimed”?: How linguistic bias affects generative language models[C]//Proc of the 26th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2021: 10080−10095, articleTitle=null, refAbstract=null), Reference(id=1327018660809519435, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=118, rfOrder=121, authorNames=null, journalName=null, refType=null, unstructuredReference=Carlini N, Tramer F, Wallace E, et al. Extracting training data from large language models[C]//Proc of the 30th USENIX Security Symp (USENIX Security 21). Berkeley, CA: USENIX Association. 2021: 2633−2650, articleTitle=null, refAbstract=null), Reference(id=1327018660893405516, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=119, rfOrder=122, authorNames=null, journalName=null, refType=null, unstructuredReference=Carlini N. A LLM assisted exploitation of AI-guardian[J]. arXiv preprint, arXiv: 2307.15008, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018660956320077, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=120, rfOrder=123, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Jiazhao, Yang Yijin, Wu Zhuofeng, et al. ChatGPT as an attack tool: Stealthy textual backdoor attack via blackbox generative model trigger[J]. arXiv preprint, arXiv: 2304.14475, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018661019234638, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=121, rfOrder=124, authorNames=null, journalName=null, refType=null, unstructuredReference=Staab R, Vero M, Balunović M, et al. Beyond memorization: Violating privacy via inference with large language models[J]. arXiv preprint, arXiv: 2310.07298, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018661077954895, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=122, rfOrder=125, authorNames=null, journalName=null, refType=null, unstructuredReference=Strubell E, Ganesh A, McCallum A. Energy and policy considerations for deep learning in NLP[C]//Proc of the 57th Annual Meeting of the ACL. Stroudsburg, PA: ACL, 2019: 3645−3650, articleTitle=null, refAbstract=null), Reference(id=1327018661145063760, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=123, rfOrder=126, authorNames=null, journalName=null, refType=null, unstructuredReference=Shumailov I, Zhao Y, Bates D, et al. Sponge examples: Energy-latency attacks on neural networks[C]//Proc of the 2021 IEEE European Symp on Security and Privacy (EuroS&P). Piscataway, NJ: IEEE, 2021: 212−231, articleTitle=null, refAbstract=null), Reference(id=1327018661207978321, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=124, rfOrder=127, authorNames=null, journalName=null, refType=null, unstructuredReference=Si W M, Backes M, Zhang Y, et al. Two-in-One: A model hijacking attack against text generation models[J]. arXiv preprint, arXiv: 2305.07406, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018661270892882, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=125, rfOrder=128, authorNames=null, journalName=null, refType=null, unstructuredReference=Tirumala K, Markosyan A H, Zettlemoyer L, et al. Memorization without overfitting: Analyzing the training dynamics of large language models[J]. arXiv preprint, arXiv: 2205.10770, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018661329613139, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=126, rfOrder=129, authorNames=null, journalName=null, refType=null, unstructuredReference=Carlini N, Chien S, Nasr M, et al. Membership inference attacks from first principles[C]//Proc of the 43rd IEEE Symp on Security and Privacy (SP). Piscataway, NJ: IEEE, 2022: 1897−1914, articleTitle=null, refAbstract=null), Reference(id=1327018661409304916, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=127, rfOrder=130, authorNames=null, journalName=null, refType=null, unstructuredReference=Fu Wenjie, Wang Huandong, Gao Chen, et al. Practical membership inference attacks against fine-tuned large language models via self-prompt calibration[J]. arXiv preprint, arXiv: 2311.06062, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018661476413781, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=128, rfOrder=131, authorNames=null, journalName=null, refType=null, unstructuredReference=Kandpal N, Pillutla K, Oprea A, et al. User inference attacks on large language models[J]. arXiv preprint, arXiv: 2310.09266, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018661543522646, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=129, rfOrder=132, authorNames=null, journalName=null, refType=null, unstructuredReference=Duan Haonan, Dziedzic A, Yaghini M, et al. On the privacy risk of in-context learning[J]. arXiv preprint, arXiv: 2411.10512, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018661606437207, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=130, rfOrder=133, authorNames=null, journalName=null, refType=null, unstructuredReference=Lehman E, Jain S, Pichotta K, et al. Does BERT pretrained on clinical notes reveal sensitive data?[J]. arXiv preprint, arXiv: 2104.07762, 2021, articleTitle=null, refAbstract=null), Reference(id=1327018661694517592, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=131, rfOrder=134, authorNames=null, journalName=null, refType=null, unstructuredReference=Kim S, Yun S, Lee H, et al. ProPILE: Probing privacy leakage in large language models[J]. arXiv preprint, arXiv: 2307.01881, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018661765820761, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=132, rfOrder=135, authorNames=null, journalName=null, refType=null, unstructuredReference=Nasr M, Carlini N, Hayase J, et al. Scalable extraction of training data from (production) language models[J]. arXiv preprint, arXiv: 2311.17035, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018661841318234, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=133, rfOrder=136, authorNames=null, journalName=null, refType=null, unstructuredReference=Pan Xudong, Zhang Mi, Ji Shouling, et al. Privacy risks of general-purpose language models[C]//Proc of the 41st IEEE Symp on Security and Privacy (SP). Piscataway, NJ: IEEE, 2020: 1314−1331, articleTitle=null, refAbstract=null), Reference(id=1327018661904232795, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=134, rfOrder=137, authorNames=null, journalName=null, refType=null, unstructuredReference=Song Congzheng, Raghunathan A. Information leakage in embedding models[C]//Proc of the 27th ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2020: 377−390, articleTitle=null, refAbstract=null), Reference(id=1327018661967147356, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=135, rfOrder=138, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Haoran, Xu Mingshi, Song Yangqiu. Sentence embedding leaks more information than You expect: Generative embedding inversion attack to recover the whole sentence[J]. arXiv preprint, arXiv: 2305.03010, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018662034256221, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=136, rfOrder=139, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang R, Hidano S, Koushanfar F. Text Revealer: Private text reconstruction via model inversion attacks against transformers[J]. arXiv preprint, arXiv: 2209.10505, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018662130725214, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=137, rfOrder=140, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Haoran, Guo Dadi, Fan Wei, et al. Multi-step jailbreaking privacy attacks on ChatGPT[J]. arXiv preprint, arXiv: 2304.05197, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018662214611295, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=138, rfOrder=141, authorNames=null, journalName=null, refType=null, unstructuredReference=Shokri R, Stronati M, Song Congzheng, et al. Membership inference attacks against machine learning models[C]//Proc of the 38th IEEE Symp on Security and Privacy (SP). Piscataway, NJ: IEEE, 2017: 3−18, articleTitle=null, refAbstract=null), Reference(id=1327018662294303072, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=139, rfOrder=142, authorNames=null, journalName=null, refType=null, unstructuredReference=Mireshghallah F, Goyal K, Uniyal A, et al. Quantifying privacy risks of masked language models using membership inference attacks[C]//Proc of the 27th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2022: 8332−8347, articleTitle=null, refAbstract=null), Reference(id=1327018662365606241, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=140, rfOrder=143, authorNames=null, journalName=null, refType=null, unstructuredReference=Carlini N, Ippolito D, Jagielski M, et al. Quantifying memorization across neural language models[J]. arXiv preprint, arXiv: 2202.07646, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018662449492322, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=141, rfOrder=144, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Jie, Shao Hanyin, Chang K C C. Are large pre-trained language models leaking your personal information?[J]. arXiv preprint, arXiv: 2205.12628, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018662520795491, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=142, rfOrder=145, authorNames=null, journalName=null, refType=null, unstructuredReference=Gupta S, Huang Y, Zhong Z, et al. Recovering private text in federated learning of language models[J]. arXiv preprint, arXiv: 2205.08514, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018662592098660, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=143, rfOrder=146, authorNames=null, journalName=null, refType=null, unstructuredReference=Krishna K, Tomar G S, Parikh A P, et al. Thieves on sesame street! Model extraction of BERT-based APIs[J]. arXiv preprint, arXiv: 1910.12366, 2020, articleTitle=null, refAbstract=null), Reference(id=1327018662650818917, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=144, rfOrder=147, authorNames=null, journalName=null, refType=null, unstructuredReference=He Xuanli, Lyu Lingjuan, Xu Qiongkai, et al. Model extraction and adversarial transferability, your BERT is vulnerable![J]. arXiv preprint, arXiv: 2103.10013, 2021, articleTitle=null, refAbstract=null), Reference(id=1327018662705344870, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=145, rfOrder=148, authorNames=null, journalName=null, refType=null, unstructuredReference=Dziedzic A, Boenisch F, Jiang M, et al. Sentence embedding encoders are easy to steal but hard to defend[C]//Proc of the 11th ICLR Workshop on Pitfalls of Limited Data and Computation for Trustworthy ML. Lausanne, Switzerland: ICLR Foundation. 2023: 2364−2378, articleTitle=null, refAbstract=null), Reference(id=1327018662772453735, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=146, rfOrder=149, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Qiongkai, He Xuanli, Lyu Lingjuan, et al. Student surpasses teacher: Imitation attack for black-box NLP APIs[J]. arXiv preprint, arXiv: 2108.13873, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018662839562600, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=147, rfOrder=150, authorNames=null, journalName=null, refType=null, unstructuredReference=Zanella-Beguelin S, Tople S, Paverd A, et al. Grey-box extraction of natural language models[C]//Proc of the 38th Int Conf on Machine Learning. New York: PMLR, 2021: 12278−12286, articleTitle=null, refAbstract=null), Reference(id=1327018662902477161, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=148, rfOrder=151, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Yi, Shi Chenghui, Ma Oubo, et al. Text laundering: Mitigating malicious features through knowledge distillation of large foundation models[C]//Proc of the 19th Int Conf on Information Security and Cryptology. Singapore: Springer Nature Singapore, 2023: 3−23, articleTitle=null, refAbstract=null), Reference(id=1327018662969586026, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=149, rfOrder=152, authorNames=null, journalName=null, refType=null, unstructuredReference=Gudibande A, Wallace E, Snell C, et al. The false promise of imitating proprietary LLMs[J]. arXiv preprint, arXiv: 2305.15717, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018663028306283, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=150, rfOrder=153, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Yiming, Carlini N, Ippolito D. Effective prompt extraction from language models[J]. arXiv preprint, arXiv: 2307.06865, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018663091220844, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=151, rfOrder=154, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Yong, Zhang Xuhong, Jiang Yi, et al. PRSA: Prompt reverse stealing attacks against large language models[J]. arXiv preprint, arXiv: 2402.19200, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018663154135405, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=152, rfOrder=155, authorNames=null, journalName=null, refType=null, unstructuredReference=Sha Zeyang, Zhang Yang. Prompt stealing attacks against large language models[J]. arXiv preprint, arXiv: 2402.12959, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018663309324654, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=153, rfOrder=156, authorNames=null, journalName=null, refType=null, unstructuredReference=Morris J X, Zhao Wenting, Chiu J T, et al. Language model inversion[J]. arXiv preprint, arXiv: 2311.13647, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018663380627823, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=154, rfOrder=157, authorNames=null, journalName=null, refType=null, unstructuredReference=Cheng Yong, Jiang Lu, Macherey W, et al. AdvAug: Robust adversarial augmentation for neural machine translation[C]//Proc of the 58th Annual Meeting of the ACL. Stroudsburg, PA: ACL, 2020: 5961−5970, articleTitle=null, refAbstract=null), Reference(id=1327018663481291120, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=155, rfOrder=158, authorNames=null, journalName=null, refType=null, unstructuredReference=Minervini P, Riedel S. Adversarially regularising neural NLI models to integrate logical background knowledge[J]. arXiv preprint, arXiv: 1808.08609, 2018, articleTitle=null, refAbstract=null), Reference(id=1327018665142235505, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=156, rfOrder=159, authorNames=null, journalName=null, refType=null, unstructuredReference=Du Tianyu, Ji Shouling, Shen Lujia, et al. Cert-RNN: Towards certifying the robustness of recurrent neural networks[C]//Proc of the 28th ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2021: 516−534, articleTitle=null, refAbstract=null), Reference(id=1327018665226121586, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=157, rfOrder=160, authorNames=null, journalName=null, refType=null, unstructuredReference=Qi Fanchao, Chen Yangyi, Li Mukai, et al. ONION: A simple and effective defense against textual backdoor attacks[C]//Proc of the 26th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2021: 9558−9566, articleTitle=null, refAbstract=null), Reference(id=1327018665289036147, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=158, rfOrder=161, authorNames=null, journalName=null, refType=null, unstructuredReference=Azizi A, Tahmid I A, Waheed A, et al. T-Miner: A generative approach to defend against trojan attacks on DNN-based text classification[C]//Proc of the 30th USENIX Security Symp (USENIX Security 21). Berkeley, CA: USENIX Association, 2021: 2255−2272, articleTitle=null, refAbstract=null), Reference(id=1327018665351950708, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=159, rfOrder=162, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Yige, Lyu Xixiang, Koren N, et al. Neural attention distillation: Erasing backdoor triggers from deep neural networks[J]. arXiv preprint, arXiv: 2101.05930, 2021, articleTitle=null, refAbstract=null), Reference(id=1327018665410670965, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=160, rfOrder=163, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Kang, Dolan-Gavitt B, Garg S. Fine-pruning: Defending against backdooring attacks on deep neural networks[J]. arXiv preprint, arXiv: 1805.12185, 2018, articleTitle=null, refAbstract=null), Reference(id=1327018665477779830, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=161, rfOrder=164, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Chang, Wang Jun, Guzmán F, et al. Mitigating data poisoning in text classification with differential privacy[C]//Proc of the 26th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2021: 4348−4356, articleTitle=null, refAbstract=null), Reference(id=1327018665536500087, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=162, rfOrder=165, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Chuanshuai, Dai Jiazhu. Mitigating backdoor attacks in LSTM-based text classification systems by backdoor keyword identification[J]. Neurocomputing, 2021, 452: 253−262, articleTitle=null, refAbstract=null), Reference(id=1327018665599414648, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=163, rfOrder=166, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Yuxia, Li Haonan, Han Xudong, et al. Do-Not-Answer: A dataset for evaluating safeguards in LLMs[J]. arXiv preprint, arXiv: 2308.13387, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018665670717817, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=164, rfOrder=167, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Mi, Pan Xudong, Yang Min. JADE: A linguistics-based safety evaluation platform for large language models[J]. arXiv preprint, arXiv: 2311.00286, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018665725243770, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=165, rfOrder=168, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Mengru, Zhang Ningyu, Xu Ziwen, et al. Detoxifying large language models via knowledge editing[J]. arXiv preprint, arXiv: 2403.14472, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018665792352635, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=166, rfOrder=169, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Jiefeng, Yoon J, Ebrahimi S, et al. Adaptation with self-evaluation to improve selective prediction in LLMs[J]. arXiv preprint, arXiv: 2310.11689, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018665851072892, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=167, rfOrder=170, authorNames=null, journalName=null, refType=null, unstructuredReference=Feldman P, Foulds J R, Pan S. Trapping LLM hallucinations using tagged context prompts[J]. arXiv preprint, arXiv: 2306.06085, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018665913987453, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=168, rfOrder=171, authorNames=null, journalName=null, refType=null, unstructuredReference=Duan Haonan, Dziedzic A, Papernot N, et al. Flocks of stochastic parrots: Differentially private prompt learning for large language models[J]. Advances in Neural Information Processing Systems, 2023, 36: 76852−76871, articleTitle=null, refAbstract=null), Reference(id=1327018665985290622, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=169, rfOrder=172, authorNames=null, journalName=null, refType=null, unstructuredReference=Yu Da, Naik S, Backurs A, et al. Differentially private fine-tuning of language models[J]. arXiv preprint, arXiv: 2110.06500, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018666048205183, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=170, rfOrder=173, authorNames=null, journalName=null, refType=null, unstructuredReference=Mattern J, Jin Zhijing, Weggenmann B, et al. Differentially private language models for secure data sharing[J]. arXiv preprint, arXiv: 2210.13918, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018666111119744, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=171, rfOrder=174, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Xuanqi, Liu Zhuotao. LLMs can understand encrypted prompt: Towards privacy-computing friendly transformers[J]. arXiv preprint, arXiv: 2305.18396, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018666199200129, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=172, rfOrder=175, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Yansong, Tan Zhixing, Liu Yang. Privacy-preserving prompt tuning for large language model services[J]. arXiv preprint, arXiv: 2305.06212, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018666253726082, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=173, rfOrder=176, authorNames=null, journalName=null, refType=null, unstructuredReference=Yan Ran, Li Yujun, Li Wenqian, et al. Teach large language models to forget privacy[J]. arXiv preprint, arXiv: 2401.00870, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018666312446339, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=174, rfOrder=177, authorNames=null, journalName=null, refType=null, unstructuredReference=Ippolito D, Tramèr F, Nasr M, et al. Preventing verbatim memorization in language models gives a false sense of privacy[J]. arXiv preprint, arXiv: 2210.17546, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018666383749508, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=175, rfOrder=178, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Sijia, Yao Yuanshun, Jia Jinghan, et al. Rethinking machine unlearning for large language models[J]. arXiv preprint, arXiv: 2402.08787, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018666450858373, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=176, rfOrder=179, authorNames=null, journalName=null, refType=null, unstructuredReference=Jang J, Yoon D, Yang S, et al. Knowledge unlearning for mitigating privacy risks in language models[C]//Proc of the 61st Annual Meeting of the ACL (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2023: 14389−14408, articleTitle=null, refAbstract=null), Reference(id=1327018666513772934, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=177, rfOrder=180, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Jiaao, Yang Diyi. Unlearn what you want to forget: Efficient unlearning for LLMs[C]//Proc of the 28th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2023: 12041−12052, articleTitle=null, refAbstract=null), Reference(id=1327018666580881799, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=178, rfOrder=181, authorNames=null, journalName=null, refType=null, unstructuredReference=Maini P, Feng Z, Schwarzschild A, et al. TOFU: A task of fictitious unlearning for LLMs[J]. arXiv preprint, arXiv: 2401.06121, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018666652184968, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=179, rfOrder=182, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Ruiqi, Lin Licong, Bai Yu, et al. Negative preference optimization: From catastrophic collapse to effective unlearning[J]. arXiv preprint, arXiv: 2404.05868, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018666727682441, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=180, rfOrder=183, authorNames=null, journalName=null, refType=null, unstructuredReference=Tian Bozhong, Liang Xiaozhuan, Cheng Siyuan, et al. To forget or not? Towards practical knowledge unlearning for large language models[C]//Proc of the 29th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2024: 1524−1537, articleTitle=null, refAbstract=null), Reference(id=1327018666790597002, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=181, rfOrder=184, authorNames=null, journalName=null, refType=null, unstructuredReference=Muresanu A, Thudi A, Zhang M R, et al. Unlearnable algorithms for in-context learning[J]. arXiv preprint, arXiv: 2402.00751, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018666853511563, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=182, rfOrder=185, authorNames=null, journalName=null, refType=null, unstructuredReference=Cohen R, Biran E, Yoran O, et al. Evaluating the ripple effects of knowledge editing in language models[J]. Transactions of the ACL, 2024, 12: 283−298, articleTitle=null, refAbstract=null), Reference(id=1327018666916426124, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=183, rfOrder=186, authorNames=null, journalName=null, refType=null, unstructuredReference=Yan Jianhao, Wang Futing, Li Yafu, et al. Potential and challenges of model editing for social debiasing[J]. arXiv preprint, arXiv: 2402.13462, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018666970952077, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=184, rfOrder=187, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu C Y, Wang Yaxuan, Flanigan J, et al. Large language model unlearning via embedding-corrupted prompts[J]. arXiv preprint, arXiv: 2406.07933, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018667075809678, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=185, rfOrder=188, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Xinwei, Li Junzhuo, Xu Minghui, et al. DEPN: Detecting and editing privacy neurons in pretrained language models[C]//Proc of the 28th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2023: 2875−2886, articleTitle=null, refAbstract=null), Reference(id=1327018667159695759, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=186, rfOrder=189, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Xinwei, Dong Weilong, Xu Shaoyang, et al. Mitigating privacy seesaw in large language models: Augmented privacy neuron editing via activation patching[C]//Proc of the 62nd Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2024: 5319−5332, articleTitle=null, refAbstract=null), Reference(id=1327018667226804624, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=187, rfOrder=190, authorNames=null, journalName=null, refType=null, unstructuredReference=Venditti D, Ruzzetti E S, Xompero G A, et al. Enhancing data privacy in large language models through private association editing[J]. arXiv preprint, arXiv: 2406.18221, 2024, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1327018636226703458, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, xref=1, ext=[AuthorCompanyExt(id=1327018636235092067, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636226703458, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Computer Science and Technology, Zhejiang University, Hangzhou 310007), AuthorCompanyExt(id=1327018636239286372, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636226703458, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1浙江大学计算机科学与技术学院 杭州 310007)]), AuthorCompany(id=1327018636298006629, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, xref=2, ext=[AuthorCompanyExt(id=1327018636302200934, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636298006629, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2College of Renwu, Guizhou University, Guiyang 550025), AuthorCompanyExt(id=1327018636310589543, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636298006629, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2贵州大学人民武装学院 贵阳 550025)]), AuthorCompany(id=1327018636369309800, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, xref=3, ext=[AuthorCompanyExt(id=1327018636377698409, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636369309800, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3College of Computer Science and Big Data, Fuzhou University, Fuzhou 350108), AuthorCompanyExt(id=1327018636503527530, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018636369309800, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3福州大学计算机与大数据学院 福州 350108)]), AuthorCompany(id=1327018638181249132, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, xref=4, ext=[AuthorCompanyExt(id=1327018638198026349, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018638181249132, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4Institute of Computer Application, China Academy of Engineering Physics, Mianyang, Sichuan 621054), AuthorCompanyExt(id=1327018638218997870, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018638181249132, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4中国工程物理研究院计算机应用研究所 四川绵阳 621054)]), AuthorCompany(id=1327018638315466863, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, xref=5, ext=[AuthorCompanyExt(id=1327018638323855472, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018638315466863, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
5School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an 710049), AuthorCompanyExt(id=1327018638336438385, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018638315466863, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
5西安交通大学网络空间安全学院 西安 710049)]), AuthorCompany(id=1327018638411935858, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, xref=6, ext=[AuthorCompanyExt(id=1327018638420324467, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018638411935858, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
6Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100091), AuthorCompanyExt(id=1327018638428713076, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018638411935858, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
6智能交通数据安全与隐私保护技术北京市重点实验室(北京交通大学) 北京 100091)]), AuthorCompany(id=1327018638516793462, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, xref=7, ext=[AuthorCompanyExt(id=1327018638525182071, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018638516793462, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
7College of Computer Science and Technology, Guizhou University, Guiyang 550025), AuthorCompanyExt(id=1327018638533570680, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, companyId=1327018638516793462, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
7贵州大学计算机科学与技术学院 贵阳 550025)])], figs=[ArticleFig(id=1327018643046641844, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, label=Figure 1, caption=
Security and privacy risks of LLM, figureFileSmall=BUWYTKw/4Da3lVeZio3CUA==, figureFileBig=JhbBJTCj9ZFzcJKblUSvMw==, tableContent=null), ArticleFig(id=1327018643117945013, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, label=图1, caption=
LLM安全与隐私风险, figureFileSmall=BUWYTKw/4Da3lVeZio3CUA==, figureFileBig=JhbBJTCj9ZFzcJKblUSvMw==, tableContent=null), ArticleFig(id=1327018643327660214, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, label=Figure 2, caption=
Three paradigms for deploying LLM in NLP tasks, figureFileSmall=r/2FIYxMX7KK7wI5oNFxTQ==, figureFileBig=0fu274FxZkiONBT7Ik7iRw==, tableContent=null), ArticleFig(id=1327018643398963383, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, label=图2, caption=
部署LLM应用于NLP任务的3种范式, figureFileSmall=r/2FIYxMX7KK7wI5oNFxTQ==, figureFileBig=0fu274FxZkiONBT7Ik7iRw==, tableContent=null), ArticleFig(id=1327018643453489336, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, label=Figure 3, caption=
Examples of conventional security threats to LLM, figureFileSmall=YcL3J8R+lRnhB6RHJdKWsA==, figureFileBig=/pdmO/jEqZWZB11UiEFR2g==, tableContent=null), ArticleFig(id=1327018643520598201, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, label=图3, caption=
对LLM的常规安全威胁示例, figureFileSmall=YcL3J8R+lRnhB6RHJdKWsA==, figureFileBig=/pdmO/jEqZWZB11UiEFR2g==, tableContent=null), ArticleFig(id=1327018643583512762, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, label=Figure 4, caption=
Illustration of typical adversarial sample attack, figureFileSmall=zISdHkudZMRVbXFL6ubQOw==, figureFileBig=Fcnyd44sJGVSRQginVrRXg==, tableContent=null), ArticleFig(id=1327018643688370363, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, label=图4, caption=
典型对抗样本攻击示意图, figureFileSmall=zISdHkudZMRVbXFL6ubQOw==, figureFileBig=Fcnyd44sJGVSRQginVrRXg==, tableContent=null), ArticleFig(id=1327018643747090620, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, label=Figure 5, caption=
Perturbations at different positions in prompts, figureFileSmall=6fqVhCeG8V7CA4ZLqeGyZA==, figureFileBig=hiQV8KdAkW7UDr/b2lTeIg==, tableContent=null), ArticleFig(id=1327018643810005181, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, label=图5, caption=
提示中不同位置处的扰动, figureFileSmall=6fqVhCeG8V7CA4ZLqeGyZA==, figureFileBig=hiQV8KdAkW7UDr/b2lTeIg==, tableContent=null), ArticleFig(id=1327018643889696958, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, label=Figure 6, caption=
Representative backdoor attack scenarios and methods, figureFileSmall=6rNKdrbGWFqk5aR5D/DTUw==, figureFileBig=Tlj7WGNL+NKM/9cqIL7HHQ==, tableContent=null), ArticleFig(id=1327018643965194431, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, label=图6, caption=
代表性后门攻击场景及方法, figureFileSmall=6rNKdrbGWFqk5aR5D/DTUw==, figureFileBig=Tlj7WGNL+NKM/9cqIL7HHQ==, tableContent=null), ArticleFig(id=1327018644057469120, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, label=Figure 7, caption=
Emerging security risks of LLM, figureFileSmall=Pex4l89DOn+d7yQY/QrWkQ==, figureFileBig=b40cy4h4xo1RfLJjFKhrFw==, tableContent=null), ArticleFig(id=1327018644170715329, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, label=图7, caption=
LLM新型安全风险, figureFileSmall=Pex4l89DOn+d7yQY/QrWkQ==, figureFileBig=b40cy4h4xo1RfLJjFKhrFw==, tableContent=null), ArticleFig(id=1327018644246212802, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, label=Table 1, caption=
Summary of Representative Adversarial Sample Attacks on LLMs, figureFileSmall=null, figureFileBig=null, tableContent=
范 式 | 方法 | 扰动 粒度 | 隐蔽 性 | 语义 损害 | 实验 任务 | 目标 模型 | 扰动 对象 |
|---|
| 注:C=字符,W=单词,S=句子;●=高,◑=中,○=低; □=白盒,■=黑盒; TC=文本分类,TE=文本蕴含,NLI=自然语言推断,TG=文本生成. |
常 规 微 调 | HotFlip[13] | C/W | ○ | ● | TC | □ | 样本 |
| TextBugger[14] | C/W | ○ | ● | TC | □/■ | 样本 |
| Behjati 等人[15] | W | ◑ | ◑ | TC | □ | 样本 |
| UAT[16] | W/S | ○ | ◑ | TC/NLI/TG | □ | 样本 |
| DeepWordBug[17] | C | ○ | ◑ | TC | ■ | 样本 |
| VIPER[18] | C | ◑ | ◑ | RTE/TC | ■ | 样本 |
| TextFooler[19] | W | ◑ | ○ | NLI/TC | ■ | 样本 |
| BERT-Attack[20] | W | ● | ○ | NLI/TC | ■ | 样本 |
| BAE[21] | W | ● | ○ | TC | ■ | 样本 |
| CLARE[22] | W | ● | ○ | NLI/TC | ■ | 样本 |
| Maheshwary等人[23] | W | ● | ○ | NLI/TC | ■ | 样本 |
| TextHoaxer[24] | W | ● | ○ | NLI/TC | ■ | 样本 |
提 示 学 习 | Xu 等人[25] | S | ○ | ◑ | TC | □ | 提示模板 |
| PAT[26] | W/S | ● | ○ | NLI/TC | ■ | 样本 |
| AdvICL[29] | C/W | ◑ | ● | TE/TC | ■ | 提示范例 |
| Qiang 等人[30] | W | ◑ | ◑ | TC | ■ | 提示范例 |
指 令 微 调 | PROMPTINJECT[34] | S | ◑ | ◑ | TG | ■ | 指令提示 |
| Shen 等人[35] | S | ◑ | ◑ | TG | ■ | 指令提示 |
| HOUYI[39] | S | ◑ | ◑ | TG | ■ | 指令提示 |
| Zou 等人[41] | S | ○ | ● | TG | □ | 指令提示 |
| AutoDAN [42] | S | ○ | ◑ | TG | □ | 指令提示 |
| Agent Smith[36] | 像素 | ● | ○ | TG | ■ | 图像输入 |
| InjecAgent[37] | S | ● | ○ | TG | ■ | Agent提示 |
), ArticleFig(id=1327018644346876099, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, label=表1, caption=
针对LLMs的代表性对抗样本攻击总结
, figureFileSmall=null, figureFileBig=null, tableContent=
范 式 | 方法 | 扰动 粒度 | 隐蔽 性 | 语义 损害 | 实验 任务 | 目标 模型 | 扰动 对象 |
|---|
| 注:C=字符,W=单词,S=句子;●=高,◑=中,○=低; □=白盒,■=黑盒; TC=文本分类,TE=文本蕴含,NLI=自然语言推断,TG=文本生成. |
常 规 微 调 | HotFlip[13] | C/W | ○ | ● | TC | □ | 样本 |
| TextBugger[14] | C/W | ○ | ● | TC | □/■ | 样本 |
| Behjati 等人[15] | W | ◑ | ◑ | TC | □ | 样本 |
| UAT[16] | W/S | ○ | ◑ | TC/NLI/TG | □ | 样本 |
| DeepWordBug[17] | C | ○ | ◑ | TC | ■ | 样本 |
| VIPER[18] | C | ◑ | ◑ | RTE/TC | ■ | 样本 |
| TextFooler[19] | W | ◑ | ○ | NLI/TC | ■ | 样本 |
| BERT-Attack[20] | W | ● | ○ | NLI/TC | ■ | 样本 |
| BAE[21] | W | ● | ○ | TC | ■ | 样本 |
| CLARE[22] | W | ● | ○ | NLI/TC | ■ | 样本 |
| Maheshwary等人[23] | W | ● | ○ | NLI/TC | ■ | 样本 |
| TextHoaxer[24] | W | ● | ○ | NLI/TC | ■ | 样本 |
提 示 学 习 | Xu 等人[25] | S | ○ | ◑ | TC | □ | 提示模板 |
| PAT[26] | W/S | ● | ○ | NLI/TC | ■ | 样本 |
| AdvICL[29] | C/W | ◑ | ● | TE/TC | ■ | 提示范例 |
| Qiang 等人[30] | W | ◑ | ◑ | TC | ■ | 提示范例 |
指 令 微 调 | PROMPTINJECT[34] | S | ◑ | ◑ | TG | ■ | 指令提示 |
| Shen 等人[35] | S | ◑ | ◑ | TG | ■ | 指令提示 |
| HOUYI[39] | S | ◑ | ◑ | TG | ■ | 指令提示 |
| Zou 等人[41] | S | ○ | ● | TG | □ | 指令提示 |
| AutoDAN [42] | S | ○ | ◑ | TG | □ | 指令提示 |
| Agent Smith[36] | 像素 | ● | ○ | TG | ■ | 图像输入 |
| InjecAgent[37] | S | ● | ○ | TG | ■ | Agent提示 |
), ArticleFig(id=1327018644426567876, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, label=Table 2, caption=
Summary of Representative Backdoor Attack Targeting LLMs, figureFileSmall=null, figureFileBig=null, tableContent=
| 范式 | 方法 | 扰动粒度 | 隐蔽性 | 语义损害 | 实验任务 | 模型权限 | 样本特异 | 主要特点 |
|---|
| 注:C=字符,W=单词,S=句子,I=语法或风格;●=高,◑=中,○=低;□=白盒,☒=灰盒,■=黑盒;TC=文本分类,TG=文本生成,SPC=句子对分类,QA=问答,TG=文本生成,NER=命名实体识别. 样本特异(sample-specific)指触发器是否与样本相关. |
| 常规微调 | Dai等人[43] | S | ○ | ◑ | TC | ■ | × | 子句易引起误触发 |
| Yang等人[44] | W | ◑ | ◑ | TC | □ | × | 多个单词组合作为触发器 |
| Kwon等人[45] | W | ○ | ◑ | TC | □ | × | 单个关键词作为触发器 |
| RIPPLe[46] | W | ○ | ◑ | TC | □ | × | 微调LLM前注入后门 |
| BadNL[47] | C/W/S | ● | ○ | TC | □ | × | 不同触发器粒度分析 |
| Lu等人[48] | C/W | ◑ | ◑ | TC | □ | √ | 动态触发器位置 |
| Qi等人[49] | I | ● | ○ | TC | □ | √ | 特殊语法作为触发特征 |
| Qi等人[50] | I | ● | ○ | TC | □ | √ | 语言风格作为触发特征 |
| Pan等人[51] | I | ● | ○ | TC | □ | √ | 语言风格作为触发特征 |
| Li等人[53] | W | ○ | ◑ | TC | □ | × | LLM中逐层注入后门 |
| Yang等人[54] | W | ○ | ◑ | TC/SPC | □ | × | 仅修改词嵌入向量 |
| TrojanLM[56] | W | ◑ | ◑ | TC/QA/TG | □ | × | 微调LLM前注入后门 |
| BadPre[57] | W | ○ | ◑ | TC/QA/NER | ■ | × | 下游任务未知 |
| Shen等人[58] | W | ○ | ◑ | TC | ■ | × | 下游任务未知 |
| NeuBA[59] | W | ○ | ◑ | TC | ■ | × | 下游任务未知 |
| UOR[60] | W | ○ | ◑ | TC | ■ | × | 动态后门向量表示 |
| 提示学习 | Xu 等人[25] | W | ○ | ◑ | TC | ■ | × | 〈MASK〉词元映射特殊向量 |
| Du等人[61] | W | ○ | ◑ | TC/SPC | ☒ | × | 连续提示向量组中的后门 |
| Cai等人[62] | W | ○ | ◑ | TC/QA | ☒ | √ | 连续提示向量组中的后门 |
| Zhao等人[63] | S | ● | ○ | TC | ☒ | × | 离散提示词元组作为触发器 |
| NOTABLE[64] | W | ○ | ◑ | TC | ■ | × | 离散提示词元组作为触发器 |
| 指令微调 | Xu等人[65] | S | ● | ○ | TG | ■ | × | 恶意指令作为后门 |
| Yan等人[66] | S | ● | ○ | TG | ■ | × | 训练时附加虚拟恶意指令 |
| Rando等人[67] | W | ● | ○ | TG | ■ | × | RLHF中注入后门 |
| BadAgent[69] | W | ● | ○ | TG | ■ | × | 大模型Agent中注入后门 |
| BadEdit[72] | W/S | ● | ○ | TG | □ | × | 编辑模型参数注入后门 |
| MEGen[73] | W/S | ● | ○ | TG | □ | × | 编辑模型参数注入后门 |
), ArticleFig(id=1327018644510453957, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, label=表2, caption=
针对LLMs的代表性后门攻击总结
, figureFileSmall=null, figureFileBig=null, tableContent=
| 范式 | 方法 | 扰动粒度 | 隐蔽性 | 语义损害 | 实验任务 | 模型权限 | 样本特异 | 主要特点 |
|---|
| 注:C=字符,W=单词,S=句子,I=语法或风格;●=高,◑=中,○=低;□=白盒,☒=灰盒,■=黑盒;TC=文本分类,TG=文本生成,SPC=句子对分类,QA=问答,TG=文本生成,NER=命名实体识别. 样本特异(sample-specific)指触发器是否与样本相关. |
| 常规微调 | Dai等人[43] | S | ○ | ◑ | TC | ■ | × | 子句易引起误触发 |
| Yang等人[44] | W | ◑ | ◑ | TC | □ | × | 多个单词组合作为触发器 |
| Kwon等人[45] | W | ○ | ◑ | TC | □ | × | 单个关键词作为触发器 |
| RIPPLe[46] | W | ○ | ◑ | TC | □ | × | 微调LLM前注入后门 |
| BadNL[47] | C/W/S | ● | ○ | TC | □ | × | 不同触发器粒度分析 |
| Lu等人[48] | C/W | ◑ | ◑ | TC | □ | √ | 动态触发器位置 |
| Qi等人[49] | I | ● | ○ | TC | □ | √ | 特殊语法作为触发特征 |
| Qi等人[50] | I | ● | ○ | TC | □ | √ | 语言风格作为触发特征 |
| Pan等人[51] | I | ● | ○ | TC | □ | √ | 语言风格作为触发特征 |
| Li等人[53] | W | ○ | ◑ | TC | □ | × | LLM中逐层注入后门 |
| Yang等人[54] | W | ○ | ◑ | TC/SPC | □ | × | 仅修改词嵌入向量 |
| TrojanLM[56] | W | ◑ | ◑ | TC/QA/TG | □ | × | 微调LLM前注入后门 |
| BadPre[57] | W | ○ | ◑ | TC/QA/NER | ■ | × | 下游任务未知 |
| Shen等人[58] | W | ○ | ◑ | TC | ■ | × | 下游任务未知 |
| NeuBA[59] | W | ○ | ◑ | TC | ■ | × | 下游任务未知 |
| UOR[60] | W | ○ | ◑ | TC | ■ | × | 动态后门向量表示 |
| 提示学习 | Xu 等人[25] | W | ○ | ◑ | TC | ■ | × | 〈MASK〉词元映射特殊向量 |
| Du等人[61] | W | ○ | ◑ | TC/SPC | ☒ | × | 连续提示向量组中的后门 |
| Cai等人[62] | W | ○ | ◑ | TC/QA | ☒ | √ | 连续提示向量组中的后门 |
| Zhao等人[63] | S | ● | ○ | TC | ☒ | × | 离散提示词元组作为触发器 |
| NOTABLE[64] | W | ○ | ◑ | TC | ■ | × | 离散提示词元组作为触发器 |
| 指令微调 | Xu等人[65] | S | ● | ○ | TG | ■ | × | 恶意指令作为后门 |
| Yan等人[66] | S | ● | ○ | TG | ■ | × | 训练时附加虚拟恶意指令 |
| Rando等人[67] | W | ● | ○ | TG | ■ | × | RLHF中注入后门 |
| BadAgent[69] | W | ● | ○ | TG | ■ | × | 大模型Agent中注入后门 |
| BadEdit[72] | W/S | ● | ○ | TG | □ | × | 编辑模型参数注入后门 |
| MEGen[73] | W/S | ● | ○ | TG | □ | × | 编辑模型参数注入后门 |
), ArticleFig(id=1327018644585951430, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, label=Table 3, caption=
Typical Attacks that Pose Data Privacy Threats, figureFileSmall=null, figureFileBig=null, tableContent=
| 攻击方式 | 工作 | 模型任务 | 实验模型 | 攻击目标 | 目标数据 |
|---|
| 成员推断 | Carlini等人[126] | 生成 | GPT-2 | 训练数据成员判断 | 预训练数据 |
| SPV-MIA[127] | 生成/分类 | GPT-2,GPT-J,Falcon等 | 训练数据判断 | 预训练数据/微调数据 |
| Kandpal等人[128] | 生成 | GPT-Neo | 训练数据判断 | 微调数据 |
| Duan等人[129] | 分类 | GPT-2 | 提示词内信息 | 系统提示词中数据 |
| 数据提取 | Lehman等人[130] | 生成 | BERT | PII探测 | 微调数据 |
| Carlini等人[118] | 生成 | GPT-2 | 训练数据提取 | 预训练数据 |
| ProPILE[131] | 生成 | OPT | PII探测 | 预训练数据 |
| Nasr等人[132] | 生成 | GPT-2,LLaMA,Falcon等 | 训练数据提取 | 预训练数据 |
| 模型逆向 | Pan等人[133] | 分类 | BERT,XLNet,GPT-2,RoBERTa, Ernie等 | 特征向量模式重建、关键字推理 | 输入文本 |
| Song等人[134] | 生成/分类 | BERT,ALBERT | 解码特征向量 | 输入文本 |
| Li等人[135] | 生成/分类 | BERT,RoBERta | 解码特征向量 | 输入文本 |
| Text Revealer[136] | 分类 | TinyBERT,BERT | 解码特征向量 | 微调数据 |
| 模型越狱 | Shen等人[35] | 生成 | GPT-4 | PII探测 | 预训练数据 |
| Li等人[137] | 生成 | ChatGPT | PII探测 | 预训练数据 |
), ArticleFig(id=1327018644669837511, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, label=表3, caption=
构成数据隐私威胁的典型攻击
, figureFileSmall=null, figureFileBig=null, tableContent=
| 攻击方式 | 工作 | 模型任务 | 实验模型 | 攻击目标 | 目标数据 |
|---|
| 成员推断 | Carlini等人[126] | 生成 | GPT-2 | 训练数据成员判断 | 预训练数据 |
| SPV-MIA[127] | 生成/分类 | GPT-2,GPT-J,Falcon等 | 训练数据判断 | 预训练数据/微调数据 |
| Kandpal等人[128] | 生成 | GPT-Neo | 训练数据判断 | 微调数据 |
| Duan等人[129] | 分类 | GPT-2 | 提示词内信息 | 系统提示词中数据 |
| 数据提取 | Lehman等人[130] | 生成 | BERT | PII探测 | 微调数据 |
| Carlini等人[118] | 生成 | GPT-2 | 训练数据提取 | 预训练数据 |
| ProPILE[131] | 生成 | OPT | PII探测 | 预训练数据 |
| Nasr等人[132] | 生成 | GPT-2,LLaMA,Falcon等 | 训练数据提取 | 预训练数据 |
| 模型逆向 | Pan等人[133] | 分类 | BERT,XLNet,GPT-2,RoBERTa, Ernie等 | 特征向量模式重建、关键字推理 | 输入文本 |
| Song等人[134] | 生成/分类 | BERT,ALBERT | 解码特征向量 | 输入文本 |
| Li等人[135] | 生成/分类 | BERT,RoBERta | 解码特征向量 | 输入文本 |
| Text Revealer[136] | 分类 | TinyBERT,BERT | 解码特征向量 | 微调数据 |
| 模型越狱 | Shen等人[35] | 生成 | GPT-4 | PII探测 | 预训练数据 |
| Li等人[137] | 生成 | ChatGPT | PII探测 | 预训练数据 |
), ArticleFig(id=1327018644741140680, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, label=Table 4, caption=
Comparison of Different Adversarial Sample Defense Strategies, figureFileSmall=null, figureFileBig=null, tableContent=
| 防御策略 | 方法简介 | 优点 | 局限性 |
|---|
| 对抗训练 | 训练数据中加入对抗样本以 提高模型鲁棒性 | 适用于多 种任务 | 训练效率降低 |
| 鲁棒性认证 | 提出一种方法以认证模型 在输入扰动下的稳定性 | 提供鲁棒 性保障 | 计算成本高, 适用性受限 |
), ArticleFig(id=1327018644829221065, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, label=表4, caption=
不同对抗样本防御策略的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 防御策略 | 方法简介 | 优点 | 局限性 |
|---|
| 对抗训练 | 训练数据中加入对抗样本以 提高模型鲁棒性 | 适用于多 种任务 | 训练效率降低 |
| 鲁棒性认证 | 提出一种方法以认证模型 在输入扰动下的稳定性 | 提供鲁棒 性保障 | 计算成本高, 适用性受限 |
), ArticleFig(id=1327018644908912842, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, label=Table 5, caption=
Comparison of Different Backdoor Defense Strategies, figureFileSmall=null, figureFileBig=null, tableContent=
| 防御策略 | 角度 | 方法简介 | 优点 | 局限性 |
|---|
| 数据筛选 | 数据 | 训练剔除毒性数据,推理过滤特征样本 | 有效防止后门触发 | 依赖特征识别精度 |
| 文本清洗 | 数据 | 利用转述消除可能的触发特征 | 简便适用,适合推理阶段 | 对复杂触发器效果有限 |
| 后门检测 | 模型 | 生成模型识别并过滤后门特征 | 有效识别异常特征 | 计算成本高 |
| 知识蒸馏 | 模型 | 利用注意力蒸馏技术淡化后门触发模式 | 无需修改结构,适用广泛 | 影响模型性能 |
| 精剪 | 模型 | 剪除对干净样本影响小的神经元 | 降低后门激活概率,保持精度 | 模型可用性受损 |
), ArticleFig(id=1327018645001187531, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, label=表5, caption=
不同后门防御策略的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 防御策略 | 角度 | 方法简介 | 优点 | 局限性 |
|---|
| 数据筛选 | 数据 | 训练剔除毒性数据,推理过滤特征样本 | 有效防止后门触发 | 依赖特征识别精度 |
| 文本清洗 | 数据 | 利用转述消除可能的触发特征 | 简便适用,适合推理阶段 | 对复杂触发器效果有限 |
| 后门检测 | 模型 | 生成模型识别并过滤后门特征 | 有效识别异常特征 | 计算成本高 |
| 知识蒸馏 | 模型 | 利用注意力蒸馏技术淡化后门触发模式 | 无需修改结构,适用广泛 | 影响模型性能 |
| 精剪 | 模型 | 剪除对干净样本影响小的神经元 | 降低后门激活概率,保持精度 | 模型可用性受损 |
), ArticleFig(id=1327018645059907788, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, label=Table 6, caption=
Comparison of Poisoning Attack Defense Strategies, figureFileSmall=null, figureFileBig=null, tableContent=
| 防御策略 | 方法简介 | 优点 | 局限性 |
|---|
| 梯度整形 | 利用差分隐私裁剪与 噪声抵御投毒攻击 | 提高鲁棒性 | 增加计算复杂度 |
| 关键词检测 | 移除后门关键词, 清理投毒样本 | 简单有效 | 依赖关键词, 适用性有限 |
), ArticleFig(id=1327018645122822349, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, label=表6, caption=
投毒攻击防御策略的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 防御策略 | 方法简介 | 优点 | 局限性 |
|---|
| 梯度整形 | 利用差分隐私裁剪与 噪声抵御投毒攻击 | 提高鲁棒性 | 增加计算复杂度 |
| 关键词检测 | 移除后门关键词, 清理投毒样本 | 简单有效 | 依赖关键词, 适用性有限 |
), ArticleFig(id=1327018645181542606, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, label=Table 7, caption=
Comparison of Content Detection in Prevention, figureFileSmall=null, figureFileBig=null, tableContent=
| 适用场景 | 防御策略 | 方法简介 | 优点 | 局限性 |
|---|
| 内容合规检测 | 静态检测 | 构建静态数据集,评估风险 | 评测透明 | 时效性差 |
| 动态检测 | 基于变异进化生成动态的测试数据 | 实时检测潜在风险 | 测试成本高 |
| 幻觉缓解 | 自我评估 | 通过自我评估调整模型,以准确地选择性预测 | 提高预测可靠性 | 增加计算复杂度 |
| 标注提示 | 使用带标签的上下文提示诱导或减少幻觉生成 | 有效缓解LLM的幻觉现象 | 依赖标签设计 |
), ArticleFig(id=1327018645244457167, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, label=表7, caption=
内容检测于防范的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 适用场景 | 防御策略 | 方法简介 | 优点 | 局限性 |
|---|
| 内容合规检测 | 静态检测 | 构建静态数据集,评估风险 | 评测透明 | 时效性差 |
| 动态检测 | 基于变异进化生成动态的测试数据 | 实时检测潜在风险 | 测试成本高 |
| 幻觉缓解 | 自我评估 | 通过自我评估调整模型,以准确地选择性预测 | 提高预测可靠性 | 增加计算复杂度 |
| 标注提示 | 使用带标签的上下文提示诱导或减少幻觉生成 | 有效缓解LLM的幻觉现象 | 依赖标签设计 |
), ArticleFig(id=1327018645307371728, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=EN, label=Table 8, caption=
Comparison of Different Privacy Protection Strategies, figureFileSmall=null, figureFileBig=null, tableContent=
| 防御策略 | 方法简介 | 优点 | 局限性 |
|---|
| 差分隐私 | 添加噪声保护数据隐私 | 有效隐私保护 | 降低模型效用 |
| 同态加密 | 加密推理过程 | 保护效果理论性强 | 计算复杂度高, 资源消耗大 |
| 黑盒防御 | 通过接口控制输出, 减少数据泄露 | 不改模型结构, 适用广泛 | 被利用生成相似的数据 |
| 机器遗忘 | 重训练改变模型参数消除数据点影响 | 隐私合规, 提升用户信任 | 难以精准遗忘,降低模型效用 |
| 知识编辑 | 修改模型参数或激活 值保护敏感信息 | 开销较小,效率较高 | 难以消除隐含关联 |
), ArticleFig(id=1327018645370286289, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018631696855099, language=CN, label=表8, caption=
不同隐私保护策略的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 防御策略 | 方法简介 | 优点 | 局限性 |
|---|
| 差分隐私 | 添加噪声保护数据隐私 | 有效隐私保护 | 降低模型效用 |
| 同态加密 | 加密推理过程 | 保护效果理论性强 | 计算复杂度高, 资源消耗大 |
| 黑盒防御 | 通过接口控制输出, 减少数据泄露 | 不改模型结构, 适用广泛 | 被利用生成相似的数据 |
| 机器遗忘 | 重训练改变模型参数消除数据点影响 | 隐私合规, 提升用户信任 | 难以精准遗忘,降低模型效用 |
| 知识编辑 | 修改模型参数或激活 值保护敏感信息 | 开销较小,效率较高 | 难以消除隐含关联 |
)], attaches=null, journal=Journal(id=1324759606947315908, delFlag=0, nameCn=计算机研究与发展, nameEn=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, issn=1000-1239, eissn=null, cn=11-1777/TP, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=k2l8zgqwstuxxevFX2qxVA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Computer Research and Development, journalRemark=null, publicationField=null, createdTime=1793776903141, updatedTime=1793850698612, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Electronic Information, subjectName=null, subjectCodeEn=Electronic Information, subjectNameEn=null, picCn=k2l8zgqwstuxxevFX2qxVA==, picEn=r6k0Ry+RD+c/VXj5QarmDw==, jcr=null, cjcr=null, exts=[JournalExt(id=1325069127710286688, language=CN, name=计算机研究与发展, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698640, updatedTime=1793850698640, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1325069127777395553, language=EN, name=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698656, updatedTime=1793850698656, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1324759914146529478, websiteList=[Website(id=1325070300139892771, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN, language=CN, createTime=1793850978169, createBy=18614031015, updateTime=1793851040259, updateBy=18614031015, name=计算机研究与发展-中文, tplId=1146099689490845704, title=计算机研究与发展, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070893751349360, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=articleTextType, value=kx, createTime=1793851119697, updateTime=1793851119697, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893730377837, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=banner, value=null, createTime=1793851119692, updateTime=1793851119692, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893772320883, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=grayFlag, value=0, createTime=1793851119702, updateTime=1793851119702, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893721989228, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851119690, updateTime=1793851119690, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893784903797, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=minRunFlag, value=0, createTime=1793851119705, updateTime=1793851119705, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893742960751, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic, createTime=1793851119695, updateTime=1793851119695, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893780709492, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=silenceFlag, value=0, createTime=1793851119704, updateTime=1793851119704, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893738766446, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1793851119694, updateTime=1793851119694, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893755543665, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeColor, value=null, createTime=1793851119698, updateTime=1793851119698, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893763932274, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeStyle, value=null, createTime=1793851119700, updateTime=1793851119700, creator=18614031015, updator=18614031015)]), Website(id=1325070300580294698, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN, language=EN, createTime=1793850978274, createBy=18614031015, updateTime=1793851036638, updateBy=18614031015, name=计算机研究与发展-英文, tplId=1146101810881728533, title=Journal of Computer Research and Development, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070925288321148, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=articleTextType, value=kx, createTime=1793851127216, updateTime=1793851127216, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925263155321, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=banner, value=null, createTime=1793851127210, updateTime=1793851127210, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925309292671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=grayFlag, value=0, createTime=1793851127221, updateTime=1793851127221, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925254766712, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851127208, updateTime=1793851127208, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925326069889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=minRunFlag, value=0, createTime=1793851127225, updateTime=1793851127225, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925279932539, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic, createTime=1793851127214, updateTime=1793851127214, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925317681280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=silenceFlag, value=0, createTime=1793851127223, updateTime=1793851127223, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925271543930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1793851127212, updateTime=1793851127212, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925292515453, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeColor, value=null, createTime=1793851127217, updateTime=1793851127217, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925300904062, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeStyle, value=null, createTime=1793851127219, updateTime=1793851127219, creator=18614031015, updator=18614031015)])], journalTitle=计算机研究与发展, weixinUrl=null, journalUrl=https://crad.ict.ac.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Computer Research and Development, journalPhotoCn=k2l8zgqwstuxxevFX2qxVA==, journalPhotoEn=r6k0Ry+RD+c/VXj5QarmDw==, journalFirstLetter=J, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202440265, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202440265, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202440265, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202440265, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1753977600000, fullTextJson=null, articleText=null, reference=null)