Article(id=1327011123464876051, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327011123016085523, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202440630, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1721491200000, receivedDateStr=2024-07-21, revisedDate=1737302400000, revisedDateStr=2025-01-20, acceptedDate=null, acceptedDateStr=null, onlineDate=1794313706508, onlineDateStr=2026-11-10, pubDate=1740758400000, pubDateStr=2025-03-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794313706508, onlineIssueDateStr=2026-11-10, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794313706508, creator=13701087609, updateTime=1794313706508, updator=13701087609, issue=Issue{id=1327011123016085523, tenantId=1146029695717560320, journalId=1324759914146529478, year='2025', volume='62', issue='3', pageStart='543', pageEnd='819', issueExtLink='null', onlineDate='null', pubDate='1740758400000', pubDateStr='2025-03-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794313706401, creator='13701087609', updateTime=1794376726899, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1327275450650440506, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327011123016085523, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1327275450650440507, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327011123016085523, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=563, endPage=588, ext={EN=ArticleExt(id=1327011123741700117, articleId=1327011123464876051, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Survey of Adversarial Attacks and Defenses for Large Language Models, columnId=1327011123649425428, journalTitle=Journal of Computer Research and Development, columnName=Special Issue on Storage Management and Data Analysis in the Era of Large Language Models, runingTitle=null, highlight=null, articleAbstract=
With the rapid development of natural language processing and deep learning technologies, large language models (LLMs) have been increasingly applied in various fields such as text processing, language understanding, image generation, and code auditing. These models have become a research hotspot of common interest in both academia and industry. However, adversarial attack methods allow attackers to manipulate large language models into generating erroneous, unethical, or false content, posing increasingly severe security threats to these models and their wide-ranging applications. This paper systematically reviews recent advancements in adversarial attack methods and defense strategies for large language models. It provides a detailed summary of fundamental principles, implementation techniques, and major findings from relevant studies. Building on this foundation, the paper delves into technical discussions of four mainstream attack modes: prompt injection attacks, indirect prompt injection attacks, jailbreak attacks, and backdoor attacks. Each is analyzed in terms of its mechanisms, impacts, and potential risks. Furthermore, the paper discusses the current research status and future directions of large language models security, and outlooks the application prospects of large language models combined with multimodal data analysis and integration technologies. This review aims to enhance understanding of the field and foster more secure, reliable applications of large language models.
, authors=Jianwei Tai
1, Shuangning Yang
1, Jiajia Wang
1, Yakai Li
2, Qixu Liu
2, Xiaoqi Jia
2, *, authorsList=Jianwei Tai, Shuangning Yang, Jiajia Wang, Yakai Li, Qixu Liu, Xiaoqi Jia, authorCompany=null, correspAuthors=Xiaoqi Jia, authorNote=
born in 1993. PhD, lecturer. Senior member of CCF. His main research interests include artificial intelligence applications, intelligent decision making and security in cyberspace. (24012@ahu.edu.cn)
born in 2003. Master candidate. His main research interest includes large language model security
born in 2004. Undergraduate. Her main research interest includes cyberspace security
born in 1997. PhD candidate. His main research interests include artificial intelligence security and deep learning interpretability
born in 1984. PhD, professor. His main research interests include Web security and vulnerability mining
born in 1982. PhD, professor. His main research interests include network attack and defence, operating system security, and cloud computing security
, 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=1327011127965364278, articleId=1327011123464876051, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=大语言模型对抗性攻击与防御综述, columnId=1327011123825586198, journalTitle=计算机研究与发展, columnName=大模型时代的存储管理与数据分析专题, runingTitle=null, highlight=null, articleAbstract=
随着自然语言处理与深度学习技术的快速发展,大语言模型在文本处理、语言理解、图像生成和代码审计等领域中的应用不断深入,成为了当前学术界与工业界共同关注的研究热点. 然而,攻击者可以通过对抗性攻击手段引导大语言模型输出错误的、不合伦理的或虚假的内容,使得大语言模型面临的安全威胁日益严峻. 对近年来针对大语言模型的对抗性攻击方法和防御策略进行总结,详细梳理了相关研究的基本原理、实施方法与研究结论. 在此基础上,对提示注入攻击、间接提示注入攻击、越狱攻击和后门攻击这4类主流的攻击模式进行了深入的技术探讨. 更进一步地,对大语言模型安全的研究现状与未来方向进行了探讨,并展望了大语言模型结合多模态数据分析与集成等技术的应用前景.
, authors=台建玮
1, 杨双宁
1, 王佳佳
1, 李亚凯
2, 刘奇旭
2, 贾晓启
2, *, authorsList=台建玮, 杨双宁, 王佳佳, 李亚凯, 刘奇旭, 贾晓启, authorCompany=null, correspAuthors=贾晓启, authorNote=
 |
1993年生. 博士,讲师. CCF高级会员. 主要研究方向为人工智能应用、智能决策与网络空间安全 |
 |
2003年生. 硕士研究生. 主要研究方向为大语言模型安全 |
 |
2004年生. 本科生. 主要研究方向为网络空间安全 |
 |
1997年生. 博士研究生. 主要研究方向为人工智能安全、深度学习可解释性 |
 |
1984年生. 博士. 教授. 主要研究方向为Web安全、漏洞挖掘 |
 |
1982年生. 博士. 教授. 主要研究方向为网络攻防技术、操作系统安全、云计算安全 |
, 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=yuB49i49otRmBUG8zhX/Jg==, magXml=N1c0hvJmRZ9+45adgmUghg==, pdfUrl=null, pdf=pdo80tvz525NkN67lztzAA==, pdfFileSize=1361507, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=LvNwWtG3mWG23wUf4tgR+A==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=CvZU05nHZNCM9zWTAqKWpw==, mapNumber=null, fund=null)}, authors=[Author(id=1327011128766476350, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=24012@ahu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327011128846168128, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, authorId=1327011128766476350, language=EN, stringName=Jianwei Tai, firstName=Jianwei, middleName=null, lastName=Tai, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1School of Internet, Anhui University, Hefei 230039, bio={"content":"
born in 1993. PhD, lecturer. Senior member of CCF. His main research interests include artificial intelligence applications, intelligent decision making and security in cyberspace. (24012@ahu.edu.cn)
"}, bioImg=null, bioContent=
born in 1993. PhD, lecturer. Senior member of CCF. His main research interests include artificial intelligence applications, intelligent decision making and security in cyberspace. (24012@ahu.edu.cn)
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327011128984580161, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, authorId=1327011128766476350, language=CN, stringName=台建玮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1安徽大学互联网学院 合肥 230039, bio={"img":"sZyIQ0FOr95QgkI9mwV9zw==","content":"
1993年生. 博士,讲师. CCF高级会员. 主要研究方向为人工智能应用、智能决策与网络空间安全
"}, bioImg=sZyIQ0FOr95QgkI9mwV9zw==, bioContent=
1993年生. 博士,讲师. CCF高级会员. 主要研究方向为人工智能应用、智能决策与网络空间安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327011128233799735, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, xref=1, ext=[AuthorCompanyExt(id=1327011128258965560, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, companyId=1327011128233799735, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Internet, Anhui University, Hefei 230039), AuthorCompanyExt(id=1327011128284131385, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, companyId=1327011128233799735, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1安徽大学互联网学院 合肥 230039)])]), Author(id=1327011129118797891, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=1327011129223655493, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, authorId=1327011129118797891, language=EN, stringName=Shuangning Yang, firstName=Shuangning, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1School of Internet, Anhui University, Hefei 230039, bio={"content":"
born in 2003. Master candidate. His main research interest includes large language model security
"}, bioImg=null, bioContent=
born in 2003. Master candidate. His main research interest includes large language model security
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327011129366261830, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, authorId=1327011129118797891, language=CN, stringName=杨双宁, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1安徽大学互联网学院 合肥 230039, bio={"img":"NvHsCzBWfmNmu+/1rIi38Q==","content":"
2003年生. 硕士研究生. 主要研究方向为大语言模型安全
"}, bioImg=NvHsCzBWfmNmu+/1rIi38Q==, bioContent=
2003年生. 硕士研究生. 主要研究方向为大语言模型安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327011128233799735, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, xref=1, ext=[AuthorCompanyExt(id=1327011128258965560, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, companyId=1327011128233799735, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Internet, Anhui University, Hefei 230039), AuthorCompanyExt(id=1327011128284131385, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, companyId=1327011128233799735, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1安徽大学互联网学院 合肥 230039)])]), Author(id=1327011129441759304, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=1327011129580171338, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, authorId=1327011129441759304, language=EN, stringName=Jiajia Wang, firstName=Jiajia, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1School of Internet, Anhui University, Hefei 230039, bio={"content":"
born in 2004. Undergraduate. Her main research interest includes cyberspace security
"}, bioImg=null, bioContent=
born in 2004. Undergraduate. Her main research interest includes cyberspace security
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327011129714389067, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, authorId=1327011129441759304, language=CN, stringName=王佳佳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1安徽大学互联网学院 合肥 230039, bio={"img":"fViP4DxIXuZJW3JFfHx8xQ==","content":"
2004年生. 本科生. 主要研究方向为网络空间安全
"}, bioImg=fViP4DxIXuZJW3JFfHx8xQ==, bioContent=
2004年生. 本科生. 主要研究方向为网络空间安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327011128233799735, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, xref=1, ext=[AuthorCompanyExt(id=1327011128258965560, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, companyId=1327011128233799735, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Internet, Anhui University, Hefei 230039), AuthorCompanyExt(id=1327011128284131385, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, companyId=1327011128233799735, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1安徽大学互联网学院 合肥 230039)])]), Author(id=1327011131345973325, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=1327011131597631568, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, authorId=1327011131345973325, language=EN, stringName=Yakai Li, firstName=Yakai, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2Institute of Information Engineering, Chinese Academy of Sciences , Beijing 100093, bio={"content":"
born in 1997. PhD candidate. His main research interests include artificial intelligence security and deep learning interpretability
"}, bioImg=null, bioContent=
born in 1997. PhD candidate. His main research interests include artificial intelligence security and deep learning interpretability
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327011131765403729, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, authorId=1327011131345973325, language=CN, stringName=李亚凯, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2中国科学院信息工程研究所 北京 100093, bio={"img":"QCkoj2PFmJM4FaV+XgPJxQ==","content":"
1997年生. 博士研究生. 主要研究方向为人工智能安全、深度学习可解释性
"}, bioImg=QCkoj2PFmJM4FaV+XgPJxQ==, bioContent=
1997年生. 博士研究生. 主要研究方向为人工智能安全、深度学习可解释性
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327011128510623802, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, xref=2, ext=[AuthorCompanyExt(id=1327011128602898491, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, companyId=1327011128510623802, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Institute of Information Engineering, Chinese Academy of Sciences , Beijing 100093), AuthorCompanyExt(id=1327011128653230140, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, companyId=1327011128510623802, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院信息工程研究所 北京 100093)])]), Author(id=1327011131853484115, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=1327011132033839189, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, authorId=1327011131853484115, language=EN, stringName=Qixu Liu, firstName=Qixu, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2Institute of Information Engineering, Chinese Academy of Sciences , Beijing 100093, bio={"content":"
born in 1984. PhD, professor. His main research interests include Web security and vulnerability mining
"}, bioImg=null, bioContent=
born in 1984. PhD, professor. His main research interests include Web security and vulnerability mining
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327011132100948054, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, authorId=1327011131853484115, language=CN, stringName=刘奇旭, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2中国科学院信息工程研究所 北京 100093, bio={"img":"FRWCWDRpA1zmxgEUipjHuA==","content":"
1984年生. 博士. 教授. 主要研究方向为Web安全、漏洞挖掘
"}, bioImg=FRWCWDRpA1zmxgEUipjHuA==, bioContent=
1984年生. 博士. 教授. 主要研究方向为Web安全、漏洞挖掘
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327011128510623802, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, xref=2, ext=[AuthorCompanyExt(id=1327011128602898491, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, companyId=1327011128510623802, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Institute of Information Engineering, Chinese Academy of Sciences , Beijing 100093), AuthorCompanyExt(id=1327011128653230140, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, companyId=1327011128510623802, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院信息工程研究所 北京 100093)])]), Author(id=1327011132176445528, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=jiaxiaoqi@iie.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1327011132243554394, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, authorId=1327011132176445528, language=EN, stringName=Xiaoqi Jia, firstName=Xiaoqi, middleName=null, lastName=Jia, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, *, address=
2Institute of Information Engineering, Chinese Academy of Sciences , Beijing 100093, bio={"content":"
born in 1982. PhD, professor. His main research interests include network attack and defence, operating system security, and cloud computing security
"}, bioImg=null, bioContent=
born in 1982. PhD, professor. His main research interests include network attack and defence, operating system security, and cloud computing security
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327011132319051867, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, authorId=1327011132176445528, language=CN, stringName=贾晓启, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, *, address=
2中国科学院信息工程研究所 北京 100093, bio={"img":"jzCCb0mHeMpOOFAv5N38Zw==","content":"
1982年生. 博士. 教授. 主要研究方向为网络攻防技术、操作系统安全、云计算安全
"}, bioImg=jzCCb0mHeMpOOFAv5N38Zw==, bioContent=
1982年生. 博士. 教授. 主要研究方向为网络攻防技术、操作系统安全、云计算安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327011128510623802, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, xref=2, ext=[AuthorCompanyExt(id=1327011128602898491, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, companyId=1327011128510623802, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Institute of Information Engineering, Chinese Academy of Sciences , Beijing 100093), AuthorCompanyExt(id=1327011128653230140, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, companyId=1327011128510623802, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院信息工程研究所 北京 100093)])])], keywords=[Keyword(id=1327011132545544284, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, orderNo=1, keyword=large language models (LLMs)), Keyword(id=1327011132625236061, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, orderNo=2, keyword=adversarial attack), Keyword(id=1327011132709122142, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, orderNo=3, keyword=defense strategy), Keyword(id=1327011133078220895, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, orderNo=4, keyword=cyberspace security), Keyword(id=1327011133262770272, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, orderNo=5, keyword=generative artificial intelligence), Keyword(id=1327011133334073441, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, orderNo=1, keyword=大语言模型), Keyword(id=1327011133409570914, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, orderNo=2, keyword=对抗性攻击), Keyword(id=1327011133547982947, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, orderNo=3, keyword=防御策略), Keyword(id=1327011133606703204, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, orderNo=4, keyword=网络空间安全), Keyword(id=1327011133795446885, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, orderNo=5, keyword=生成式人工智能)], refs=[Reference(id=1327011141450051719, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Matthew H. Hackers easily fool artificial intelligences-adversarial attacks highlight lack of security in machine learning algorithms[J]. Science, 2018, 361(6399): 215−215, articleTitle=null, refAbstract=null), Reference(id=1327011141563297928, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Romera-Paredes B, Barekatain M, Novikov A, et al. Mathematical discoveries from program search with large language models[J]. Nature, 2024, 625(7995): 468−475, articleTitle=null, refAbstract=null), Reference(id=1327011141722681481, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Radford A, Wu J, Child R, et al. OpenAI blog: Language models are unsupervised multitask learners [EB/OL]. 2024[2024-08-10]. https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf, articleTitle=null, refAbstract=null), Reference(id=1327011141823344778, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Koroteev M V. BERT: A review of applications in natural language processing and understanding[J]. arXiv preprint, arXiv: 2103.11943, 2021, articleTitle=null, refAbstract=null), Reference(id=1327011141974339723, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Touvron H, Lavril T, Izacard G, et al. LLaMA: Open and efficient foundation language models[J]. arXiv preprint, arXiv: 2302.13971, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011142070808716, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=虎嵩林,李涓子,秦兵,等. 亦正亦邪大模型——大模型与安全专题导读[J]. 计算机研究与发展,2024,61(5):1085−1093, articleTitle=null, refAbstract=null), Reference(id=1327011142184054925, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Hu Songlin, Li Juanzi, Qin Bing, et al. The double-edged swords: An introduction to the special issue on large models and safety[J]. Journal of Computer Research and Development, 2024, 61(5): 1085−1093 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327011142288912526, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Lin S, Hilton J, Evans O. TruthfulQA: Measuring how models mimic human falsehoods[C]//Proc of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2022: 3214−3252, articleTitle=null, refAbstract=null), Reference(id=1327011142452490383, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Bommasani R, Hudson D A, Adeli E, et al. On the opportunities and risks of foundation models[J]. arXiv preprint, arXiv: 2108.07258, 2021, articleTitle=null, refAbstract=null), Reference(id=1327011142565736592, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Weidinger L, Mellor J, Rauh M, et al. Ethical and social risks of harm from language models[J]. arXiv preprint, arXiv: 2112.04359, 2021, articleTitle=null, refAbstract=null), Reference(id=1327011142641234065, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Hou Xinyi, Zhao Yanjie, Wang Haoyu. On the (in)security of LLM app stores[J]. arXiv preprint, arXiv: 2407.08422, 2024, articleTitle=null, refAbstract=null), Reference(id=1327011142733508754, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Achintalwar S, Garcia A A, Anaby-tavor A, et al. Detectors for safe and reliable LLMs: Implementations, uses, and limitations[J]. arXiv preprint, arXiv: 2403.06009, 2024, articleTitle=null, refAbstract=null), Reference(id=1327011142800617619, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=王笑尘,张坤,张鹏. 多视角看大模型安全及实践[J]. 计算机研究与发展,2024,61(5):1104−1112, articleTitle=null, refAbstract=null), Reference(id=1327011142863532180, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Xiaochen, Zhang Kun, Zhang Peng. Large model safety and practice from multiple perspectives[J]. Journal of Computer Research and Development, 2024, 61(5): 1104−1112 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327011142943223957, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Jacob D, Chang Mingwei, Kenton L, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[C]//Proc of the 2019 Conf of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Stroudsburg, PA: ACL, 2019: 4171–4186, articleTitle=null, refAbstract=null), Reference(id=1327011143064858774, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Wei J, Bosma M, Zhao V, et al. Finetuned language models are zero-shot learners[C/OL]//Proc of the 10th Int Conf on Learning Representations. Washington: ICLR, 2022[2024-08-11]. https://iclr.cc/virtual/2022/oral/6255, articleTitle=null, refAbstract=null), Reference(id=1327011143119384727, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Ziegler D M, Stiennon N, Wu J, et al. Fine-tuning language models from human preferences[J]. arXiv preprint, arXiv: 1909.08593, 2019, articleTitle=null, refAbstract=null), Reference(id=1327011144805494936, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Mao Xiaofeng, Chen Yuefeng, Jia Xiaojun, et al. Context-aware robust fine-tuning[J]. International Journal of Computer Vision, 2024, 132(5): 1685−1700, articleTitle=null, refAbstract=null), Reference(id=1327011144901963929, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Kai Feng, Huang Lan, Wang Kanping, et al. Prompt-based learning framework for zero-shot cross-lingual text classification[J]. Engineering Applications of Artificial Intelligence, 2024, 133(E): 108481, articleTitle=null, refAbstract=null), Reference(id=1327011144981655707, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Buckner C. Understanding adversarial examples requires a theory of artefacts for deep learning[J]. Nature Machine Intelligence, 2020, 2(12): 731−736, articleTitle=null, refAbstract=null), Reference(id=1327011145057153180, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Liang Hongshuo, He Erlu, Zhao Yangyang, et al. Adversarial attack and defense: A survey[J]. Electronics, 2022, 11(8): 1283−1301, articleTitle=null, refAbstract=null), Reference(id=1327011145145233565, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=21, 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=1327011145241702558, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=22, 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=1327011145346560159, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Sarabadani A, Halfaker A, Taraborelli D. Building automated vandalism detection tools for Wikidata [C]//Proc of the 26th Int Conf on World Wide Web Companion. New York: ACM, 2017: 1647−1654, articleTitle=null, refAbstract=null), Reference(id=1327011145438834848, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proc of the 30th Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 2017: 5998−6008, articleTitle=null, refAbstract=null), Reference(id=1327011145518526625, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Lan Jiahe, Wang Jie, Yan Baochen, et al. FlowMur: A stealthy and practical audio backdoor attack with limited knowledge[C]//Proc of the 2024 IEEE Symp on Security and Privacy (SP). Piscataway, NJ: IEEE, 2024: 1646−1664, articleTitle=null, refAbstract=null), Reference(id=1327011145602412706, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Jayaraman B, Ghosh E, Chase M, et al. Combing for credentials: Active pattern extraction from smart reply[C]//Proc of the 2024 IEEE Symp on Security and Privacy (SP). Piscataway, NJ: IEEE, 2024: 1443−1461, articleTitle=null, refAbstract=null), Reference(id=1327011145673715875, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Mor G, Daniel K, Elad S, et al. Did aristotle use a laptop? A question answering benchmark with implicit reasoning strategies[J]. Transations of the Association for Computational Linguistics, 2021, 9: 346−361, articleTitle=null, refAbstract=null), Reference(id=1327011145757601956, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Laurencon H, Saylnier L, Thomas W, et al. The BigScience ROOTS Corpus: A 1.6TB composite multilingual dataset[C]//Proc of the 35th Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 2022: 31809−31826, articleTitle=null, refAbstract=null), Reference(id=1327011145820516517, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Yuan Sha, Zhao Hanyu, Du Zhengxiao, et al. WuDaoCorpora: A super large-scale Chinese corpora for pre-training language models[J]. AI Open, 2021, 2: 65−68, articleTitle=null, refAbstract=null), Reference(id=1327011145904402598, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Wan Jie, Fu Jianhao, Wang Lijin, et al. BounceAttack: A query-efficient decision-based adversarial attack by bouncing into the wild[C]//Proc of the 2024 IEEE Symp on Security and Privacy (SP). San Piscataway, NJ: IEEE, 2024: 1270−1286, articleTitle=null, refAbstract=null), Reference(id=1327011146013454503, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Forest A, Matthew H, Peter S, et al. Learning activation functions to improve deep neural networks [J]. arXiv preprint, arXiv: 1412.6830, 2014, articleTitle=null, refAbstract=null), Reference(id=1327011146126700712, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Henighan T, Kaplan J, Katz M, et al. Scaling laws for autoregressive generative modeling[J]. arXiv preprint, arXiv: 2010.14701, 2020, articleTitle=null, refAbstract=null), Reference(id=1327011146202198185, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Agrawal K, Bhatnagar C. M-SAN: A patch-based transferable adversarial attack using the multi-stack adversarial network[J]. Journal of Electronic Imaging, 2023, 32(2): 023033, articleTitle=null, refAbstract=null), Reference(id=1327011146273501355, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Tao G, Wang Zhenting, Feng Shiwei, et al. Distribution preserving backdoor attack in self-supervised learning[C]//Proc of the 2024 IEEE Symp on Security and Privacy (SP). Piscataway, NJ: IEEE, 2024: 2029−2047, articleTitle=null, refAbstract=null), Reference(id=1327011146353193132, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Priyan V, Zhang Tianyi, Elena L. Expectation vs experience: Evaluating the usability of code generation tools powered by large language models[C]//Proc of the 2022 Chi Conf on Human Factors in Computing Systems Extended Abstracts. New York: ACM, 2022: 332: 1−332: 7, articleTitle=null, refAbstract=null), Reference(id=1327011146437079213, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Zhang Junjie, Xie Ruobing, Hou Yupeng, et al. Recommendation as instruction following: A large language model empowered recommendation approach[J]. arXiv preprint, arXiv: 2305.07001, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011146508382382, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Goodfellow I J, Shlens J, Szegedy C. Explaining and harnessing adversarial examples[J]. arXiv preprint, arXiv: 1412.6572, 2014, articleTitle=null, refAbstract=null), Reference(id=1327011146583879855, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Szegedy C, Zaremba W, Sutskever I, et al. Intriguing properties of neural networks[J]. arXiv preprint, arXiv: 1312.6199, 2013, articleTitle=null, refAbstract=null), Reference(id=1327011146667765936, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Branch H J, Cefalu J R, Mchugh J, et al. Evaluating the susceptibility of pre-trained language models via handcrafted adversarial examples[J]. arXiv preprint, arXiv: 2209.02128, 2022, articleTitle=null, refAbstract=null), Reference(id=1327011146751652017, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=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=1327011146835538098, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Kang D, Li Xuechen, Stoica I, et al. Exploiting programmatic behavior of LLMs: Dual-use through standard security attacks[C] //Proc of the 2024 IEEE Security and Privacy Workshops (SPW). Piscataway, NJ: IEEE, 2024: 132−143, articleTitle=null, refAbstract=null), Reference(id=1327011146911035571, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Toyer S, Watkins O, Mendes E A, et al. Tensor trust: Interpretable prompt injection attacks from an online game[C/OL] //Proc of the 12th Int Conf on Learning Representations. Washington: ICLR, 2024[2024-08-12]. https://openreview.net/forum?id=fsW7wJGLBd, articleTitle=null, refAbstract=null), Reference(id=1327011146994921652, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Nccgroup. Exploring prompt injection attacks: NCC group research blog[EB/OL]. 2024[2024-08-10]. https://research.nccgroup.com/2022/12/05/exploring-prompt-injectionattacks/, articleTitle=null, refAbstract=null), Reference(id=1327011147053641909, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=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=1327011147133333686, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Pedro R, Castro D, Carreira P, et al. From prompt injections to SQL injection attacks: How protected is your LLM-integrated web application?[J]. arXiv preprint, arXiv: 2308.01990, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011147208831159, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Liu Xiaogeng, Yu Zhiyuan, Zhang Yizhe, et al. Automatic and universal prompt injection attacks against large language models[J]. arXiv preprint, arXiv: 2403.04957, 2024, articleTitle=null, refAbstract=null), Reference(id=1327011147364020408, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Zou A, Wang Zifan, Carlini N, et al. Universal and transferable adversarial attacks on aligned language models[J]. arXiv preprint, arXiv: 2307.15043, 2307, articleTitle=null, refAbstract=null), Reference(id=1327011147452100794, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Shi Jiawen, Yuan Zenghui, Liu Yinuo, et al. Optimization-based prompt injection attack to LLM-as-a-judge[J]. arXiv preprint, arXiv: 2307.15043, 2307, articleTitle=null, refAbstract=null), Reference(id=1327011147544375483, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Liu Yupei, Jia Yuqi, Geng Runpeng, et al. Formalizing and benchmarking prompt injection attacks and defenses[C] //Proc of the 33rd USENIX Security Symp (USENIX Security 24). Berkeley, CA: USENIX Association, 2024: 1831−1847, articleTitle=null, refAbstract=null), Reference(id=1327011147611484348, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Sippo R, Alisia M M, Raghava R M, et al. An early categorization of prompt injection attacks on large language models[J]. arXiv preprint, arXiv: 2402.00898, 2024, articleTitle=null, refAbstract=null), Reference(id=1327011149293400253, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Greshake K, Abdelnabi S, Mishra S, et al. More than you’ve asked for: A comprehensive analysis of novel prompt injection threats to application-integrated large language models[J]. arXiv preprint, arXiv: 2302.12137, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011149394063550, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Bagdasaryan E, Hsieh T Y, Nassi B, et al. Abusing images and sounds for indirect instruction injection in multi-modal LLMs[J]. arXiv preprint, arXiv: 2302.10490, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011149587001535, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Zhan Qiusi, Liang Zhixiang, Ying Zifan, et al. InjecAgent: Benchmarking indirect prompt injections in tool-integrated large language model agents[C]//Proc of the 2024 Findings of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2024: 10471−10506, articleTitle=null, refAbstract=null), Reference(id=1327011149704442048, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Shayegani E, Dong Yue, Abu-Ghazaleh N. Plug and pray: Exploiting off-the-shelf components of multi-modal models[J]. arXiv preprint, arXiv: 2307.14539, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011149779939521, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Liu Yi, Deng Gelei, Xu Zhengzi, et al. Jailbreaking ChatGPT via prompt engineering: An empirical study[J]. arXiv preprint, arXiv: 2305.13860, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011149842854082, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=White J, Fu Quchen, Hays S, et al. A prompt pattern catalog to enhance prompt engineering with ChatGPT[J]. arXiv preprint, arXiv: 2302.11382, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011149909962947, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Wei A, Haghtalab N, Steinhardt J. Jailbroken: How does LLM safety training fail?[C]//Proc of the 36th Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 2024: 14−46, articleTitle=null, refAbstract=null), Reference(id=1327011149968683204, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Yuan Youliang, Jiao Wenxiang, Wang Wenxuan, et al. GPT−4 is too smart to be safe: Stealthy chat with LLMs via cipher[C/OL]//Proc of the 12th Int Conf on Learning Representations. Washington: ICLR, 2024[2024-08-12]. https://openreview.net/forum?id=MbfAK4s61A, articleTitle=null, refAbstract=null), Reference(id=1327011150039986373, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Zheng Yongxin, Menghini C, Bach S. Low-resource languages jailbreak GPT−4[J]. arXiv preprint, arXiv: 2310.02446, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011150111289543, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Jiang Fengqing, Xu Zhangchen, Niu Luyao, et al. ArtPrompt: ASCII art-based jailbreak attacks against aligned LLMs[C]//Proc of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2024: 15157−15173, articleTitle=null, refAbstract=null), Reference(id=1327011150174204104, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Li Haoran, Guo Dadi, Fan Wei, et al. Multi-step jailbreaking privacy attacks on ChatGPT[C]//Proc of the 2023 Findings of the Association for Computational Linguistics: EMNLP 2023. Stroudsburg, PA: ACL, 2023: 4138−4153, articleTitle=null, refAbstract=null), Reference(id=1327011150249701577, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Wang Jiongxiao, Liu Zichen, Park K, et al. Adversarial demonstration attacks on large language models[J]. arXiv preprint, arXiv: 2305.14950, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011150400696522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Wei Zeming, Wang Yifei, Li Ang, et al. Jailbreak and guard aligned language models with only few in-context demonstrations[J]. arXiv preprint, arXiv: 2310.06387, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011150522331339, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=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=1327011150635577548, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=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=1327011150715269325, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Li Xuan, Zhou Zhanke, Zhu Jianing, et al. DeepInception: Hypnotize large language model to be jailbreaker[J]. arXiv preprint, arXiv: 2308.03191, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011150807544014, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Alayrac J B, Donahue J, Luc P, et al. Flamingo: A visual language model for few-shot learning[C]//Proc of the 35th Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 2022: 23716−23736, articleTitle=null, refAbstract=null), Reference(id=1327011150883041487, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Google. Bard[EB/OL]. 2023[2024-08-12]. https://bard.google.com/, articleTitle=null, refAbstract=null), Reference(id=1327011150966927568, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Carlini N, Nasr M, Choquette-Choo C A, et al. Are aligned neural networks adversarially aligned?[C]//Proc of the 36th Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 2024: 48−79, articleTitle=null, refAbstract=null), Reference(id=1327011151042425041, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Qi Xiangyu, Huang Kaixuan, Panda A, et al. Visual adversarial examples jailbreak large language models[J]. arXiv preprint, arXiv: 2306.13213, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011151117922514, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Schlarmann C, Hein M. On the Adversarial robustness of multi-modal foundation models[C]//Proc of the 2023 IEEE/CVF Int Conf on Computer Vision Workshops (ICCVW). Piscataway, NJ: IEEE, 2023: 3677−3685, articleTitle=null, refAbstract=null), Reference(id=1327011151185031379, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Zhao Yunqing, Pang Tianyu, Du Chao, et al. On evaluating adversarial robustness of large vision-language models[C]//Proc of the 36th Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 2024: 950−986, articleTitle=null, refAbstract=null), Reference(id=1327011151268917460, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Dong Yinpeng, Chen Huanran, Chen Jiawei, et al. How robust is Google’s bard to adversarial image attacks?[J]. arXiv preprint, arXiv: 2309.11751, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011151361192149, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Deng Gelei, Liu Yi, Li Yuekang, et al. MasterKey: Automated jailbreaking of large language model chatbots[C/OL]//Proc of the 2024 Network and Distributed System Security Symp. Rosten, VA: Internet Society, 2024[2024-08-13]. https://www.ndss-symposium.org/ndss-paper/masterkey-automated-jailbreaking-of-large-language-model-chatbots/, articleTitle=null, refAbstract=null), Reference(id=1327011151453466838, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Yao Dongyu, Zhang Jianshu, Harris I, et al. A novel and universal fuzzing framework for proactively discovering jailbreak vulnerabilities in large language models[C]//Proc of the 2024 IEEE Int Conf on Acoustics, Speech and Signal Processing (ICASSP). Piscataway, NJ: IEEE, 2024: 19−35, articleTitle=null, refAbstract=null), Reference(id=1327011151545741527, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Yu Jiahao, Lin Xingwei, Yu Zheng, et al. GPTFUZZER: Red teaming large language models with auto-generated jailbreak prompts[J]. arXiv preprint, arXiv: 2309.10253, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011151679959256, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Wang Zimu, Wang Wei, Chen Qi, et al. Generating valid and natural adversarial examples with large language models[C]//Proc of the 27th Int Conf on Computer Supported Cooperative Work in Design (CSCWD). Piscataway, NJ: IEEE, 2024: 37−69, articleTitle=null, refAbstract=null), Reference(id=1327011151801594073, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Chao P, Robey A, Dobriban E, et al. Jailbreaking black box large language models in twenty queries[J]. arXiv preprint, arXiv: 2310.08419, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011151885480154, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Mehrotra A, Zampetakis M, Kassianik P, et al. Tree of Attacks: Jailbreaking black-box LLMs automatically[J]. arXiv preprint, arXiv: 2310.02119, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011151960977627, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Liu Xiaogeng, Xu Nan, Chen Muhao, et al. AutoDAN: Generating stealthy jailbreak prompts on aligned large language models[C/OL]//Proc of the 12th Int Conf on Learning Representations. Washington: ICLR, 2024[2024-08-12]. https://openreview.net/forum?id=7Jwpw4qKkb, articleTitle=null, refAbstract=null), Reference(id=1327011152049058012, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Guo Ping, Liu Fei, Lin Xi, et al. L-AutoDA: Leveraging large language models for automated decision-based adversarial attacks[J]. arXiv preprint, arXiv: 2401.15335, 2024, articleTitle=null, refAbstract=null), Reference(id=1327011152300716253, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Li Shaofeng, Liu Hui, Dong Tian, et al. Hidden backdoors in human-centric language models[C]//Proc of the 2021 ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2021: 3123−3140, articleTitle=null, refAbstract=null), Reference(id=1327011153856803038, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Wan A, Wallace E, Shen S, et al. Poisoning language models during instruction tuning[C]//Proc of the 40th Int Conf on Machine Learning. NEW York: PMLR, 2023: 35413−35425, articleTitle=null, refAbstract=null), Reference(id=1327011153961660639, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Xu Jiashu, Ma Mingyu, Wang Fei, et al. Instructions as Backdoors: Backdoor vulnerabilities of instruction tuning for large language models[C]//Proc of the 2024 Conf of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2024: 3111−3126, articleTitle=null, refAbstract=null), Reference(id=1327011154133627104, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=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=1327011154221707489, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Hubinger E, Denison C, Mu J, et al. Sleeper agents: Training deceptive LLMs that persist through safety training[J]. arXiv preprint, arXiv: 2401.05566, 2024, articleTitle=null, refAbstract=null), Reference(id=1327011154372702434, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Shi Jiawen, Liu Yixin, Zhou Pan, et al. Badgpt: Exploring security vulnerabilities of ChatGPT via backdoor attacks to instructgpt[J]. arXiv preprint, arXiv: 2304.12298, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011154515308771, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Dong Tian, Xue Minhui, Chen Guoxing, et al. Unleashing cheapfakes through trojan plugins of large language models[J]. arXiv preprint, arXiv: 2312.00374, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011154599194852, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Xiang Zhen, Jiang Fengqing, Xiong Zidi, et al. Badchain: Backdoor chain-of-thought prompting for large language models[C/OL]//Proc of the 12th Int Conf on Learning Representations. Washington: ICLR, 2024[2024-08-13]. https://openreview.net/forum?id=c93SBwz1Ma, articleTitle=null, refAbstract=null), Reference(id=1327011154683080933, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=朱素霞,王金印,孙广路. 基于感知相似性的多目标优化隐蔽图像后门攻击[J]. 计算机研究与发展,2024,61(5):1182−1192, articleTitle=null, refAbstract=null), Reference(id=1327011154750189798, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=88, rfOrder=91, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Suxia, Wang Jinyin, Sun Guanglu. Perceptual similarity-based multi-objective optimization for stealthy image backdoor attack[J]. Journal of Computer Research and Development, 2024, 61(5): 1182−1192 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327011154821492967, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=89, rfOrder=92, authorNames=null, journalName=null, refType=null, unstructuredReference=Gabriel A, Michael K. Detecting language model attacks with perplexity[J]. arXiv preprint, arXiv: 2308.14132, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011154913767657, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=90, rfOrder=93, authorNames=null, journalName=null, refType=null, unstructuredReference=Hu Zhengmian, Wu Gang, Saayan M, et al. Token-level adversarial prompt detection based on perplexity measures and contextual information[J]. arXiv preprint, arXiv: 2311.11509, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011154989265130, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=91, rfOrder=94, authorNames=null, journalName=null, refType=null, unstructuredReference=Alon G, Kamfonas M. Detecting language model attacks with perplexity[J]. arXiv preprint, arXiv: 2308.14132, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011155081539819, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Lapid R, Langberg R, Sipper M. Open Sesame! Universal black box jailbreaking of large language models[J]. arXiv preprint, arXiv: 2309.01446, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011155207368940, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Zhu Sicheng, Zhang Ruiyi, An Bang, et al. Autodan: Automatic and interpretable adversarial attacks on large language models[J]. arXiv preprint, arXiv: 2310.15140, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011155270283501, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Robey A, Wong E, Hassani H, et al. SmoothLLM: Defending large language models against jailbreaking attacks[J]. arXiv preprint, arXiv: 2310.03684, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011155349975278, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Phute M, Helbling A, Hull M, et al. LLM Self Defense: By self examination, LLMs know they are being tricked[C/OL]//Proc of the 2th Tiny Papers Track at ICLR 2024. Washington: ICLR, 2024[2024-08-14]. https://openreview.net/forum?id=YoqgcIA19o, articleTitle=null, refAbstract=null), Reference(id=1327011155421278447, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Glukhov D, Shumailov I, Gal Y, et al. LLM Censorship: A machine learning challenge or a computer security problem?[J]. arXiv preprint, arXiv: 2307.10719, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011155538718960, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Kumar A, Agarwal C, Srinivas S, et al. Certifying LLM safety against adversarial prompting[J]. arXiv preprint, arXiv: 2309.02705, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011155605827825, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Jain N, Schwarzschild A, Wen Y, et al. Baseline defenses for adversarial attacks against aligned language models[J]. arXiv preprint, arXiv: 2309.00614, 2023, articleTitle=null, refAbstract=null), Reference(id=1327011155689713906, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Cao Bochuan, Cao Yuanpu, Lin Lu, et al. Defending against alignment-breaking attacks via robustly aligned LLM[C]//Proc of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2024: 10542−10560, articleTitle=null, refAbstract=null), Reference(id=1327011155777794291, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Wang Hao, Li Hao, Huang Minlie, et al. From noise to clarity: Unraveling the adversarial suffix of large language model attacks via translation of text embeddings[J]. arXiv preprint, arXiv: 2402.16006, 2024, articleTitle=null, refAbstract=null), Reference(id=1327011155874263284, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Ji Jiabao, Hou Bairu, Alexander R, et al. Defending large language models against jailbreak attacks via semantic smoothing[J]. arXiv preprint, arXiv: 2402.16192, 2024, articleTitle=null, refAbstract=null), Reference(id=1327011155932983541, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Liu Xiaodong, Cheng Hao, He Pengcheng, et al. Adversarial training for large neural language models[J]. arXiv preprint, arXiv: 2004.08994, 2020, articleTitle=null, refAbstract=null), Reference(id=1327011156004286710, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Ganguli D, Lovitt L, Kernion J, et al. Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned[J]. arXiv preprint, arXiv: 2209.07858, 2022, articleTitle=null, refAbstract=null), Reference(id=1327011156172058871, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Perez E, Huang S, Song F, et al. Red teaming language models with language models[C]//Proc of the 2022 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2022: 3419−3448, articleTitle=null, refAbstract=null), Reference(id=1327011156243362040, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Mitchell E, Lin C, Bosselut A. Memory-based model editing at scale [C]//Proc of the 39th Int Conf on Machine Learning. Stroudsburg, PA: ACL 2022: 15817−15831, articleTitle=null, refAbstract=null), Reference(id=1327011156310470905, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Huang Zeyu, Shen Yikang, Zhang Xiaofeng, et al. Transformer-patcher: One mistake worth one neuron[C]//Proc of the 11th Int Conf on Learning Representations. Washington: ICLR, 2024[2024-08-14]. https://openreview.net/forum?id=4oYUGeGBPm, articleTitle=null, refAbstract=null), Reference(id=1327011156381774075, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Meng K, Bau D, Andonian A, et al. Locating and editing factual associations in GPT[C]//Proc of the 35th Advances in Neural Information Processing Systems. Cambridge, MA: MIT Press, 2022: 17359−17372, articleTitle=null, refAbstract=null), Reference(id=1327011156448882940, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=Meng K, Sharma A S, Andonian A, et al. Mass-editing memory in a transformer[C]//Proc of the 11th Int Conf on Learning Representations. Washington: ICLR, 2023[2024-08-13]. https://openreview.net/forum?id=MkbcAHIYgyS, articleTitle=null, refAbstract=null), Reference(id=1327011156524380413, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, 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=王梦如,姚云志,习泽坤,等. 基于知识编辑的大模型内容生成安全分析[J]. 计算机研究与发展,2024,61(5):1143−1155, articleTitle=null, refAbstract=null), Reference(id=1327011156583100670, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=109, rfOrder=113, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Mengru, Yao Yunzhi, Xi Zekun, et al. Safety analysis of large model content generation based on knowledge editing[J]. Journal of Computer Research and Development, 2024, 61(5): 1143−1155 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327011158311153919, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=110, rfOrder=114, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Yuhui, Wei Fangyun, Zhao Jinjing, et al. RAIN: Your language models can align themselves without finetuning[C/OL]//Proc of the 12th Int Conf on Learning Representations. Washington: ICLR, 2024[2024-08-13]. https://openreview.net/forum?id=pETSfWMUzy, articleTitle=null, refAbstract=null), Reference(id=1327011158382457088, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=111, rfOrder=115, authorNames=null, journalName=null, refType=null, unstructuredReference=Kim H, Yuk S, Cho H. Break the breakout: Reinventing LM defense against jailbreak attacks with self-refinement[J]. arXiv preprint, arXiv: 2402.15180, 2024, articleTitle=null, refAbstract=null), Reference(id=1327011158457954561, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=112, rfOrder=116, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Yujun, Han Yufei, Zhuang Haomin, et al. Defending jailbreak prompts via in-context adversarial game[J]. arXiv preprint, arXiv: 2402.13148, 2024, articleTitle=null, refAbstract=null), Reference(id=1327011158541840642, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=113, rfOrder=117, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Zhangchen, Jiang Fengqing, Niu Luyao, et al. SafeDecoding: Defending against jailbreak attacks via safety-aware decoding[C]//Proc of the 62nd Annual Meeting of the ACL (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2024: 5587–5605, articleTitle=null, refAbstract=null), Reference(id=1327011158663475459, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=114, rfOrder=118, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Zhexin, Yang Junxiao, Ke Pei, et al. Defending large language models against jailbreaking attacks through goal prioritization[C]//Proc of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2024: 8865–8887, articleTitle=null, refAbstract=null), Reference(id=1327011158780915972, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=115, rfOrder=119, authorNames=null, journalName=null, refType=null, unstructuredReference=Jin Haibo, Hu Leyang, Li Xinuo , et al. JailbreakZoo: Survey, landscapes, and horizons in jailbreaking large language and vision-language models[J]. arXiv preprint, arXiv: 2407.01599, 2024, articleTitle=null, refAbstract=null), Reference(id=1327011158952882438, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=116, rfOrder=120, authorNames=null, journalName=null, refType=null, unstructuredReference=Ying Zonghao, Liu Aishan, Liu Xianglong, et al. Unveiling the safety of GPT−4o: An empirical study using jailbreak attacks[J]. arXiv preprint, arXiv: 2406.06302, 2024, articleTitle=null, refAbstract=null), Reference(id=1327011159045157127, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=117, rfOrder=121, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Junyang, Xu Haiyang, Jia Haitao, et al. Mobile-Agent: Autonomous multi-modal mobile device agent with visual perception[J]. arXiv preprint, arXiv: 2401.16158, 2024, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1327011128233799735, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, xref=1, ext=[AuthorCompanyExt(id=1327011128258965560, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, companyId=1327011128233799735, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1School of Internet, Anhui University, Hefei 230039), AuthorCompanyExt(id=1327011128284131385, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, companyId=1327011128233799735, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1安徽大学互联网学院 合肥 230039)]), AuthorCompany(id=1327011128510623802, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, xref=2, ext=[AuthorCompanyExt(id=1327011128602898491, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, companyId=1327011128510623802, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Institute of Information Engineering, Chinese Academy of Sciences , Beijing 100093), AuthorCompanyExt(id=1327011128653230140, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, companyId=1327011128510623802, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院信息工程研究所 北京 100093)])], figs=[ArticleFig(id=1327011134168739943, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, label=Figure 1, caption=
Framework diagram of our paper, figureFileSmall=PieiWSjIclD3y+uz1ydJng==, figureFileBig=LvNwWtG3mWG23wUf4tgR+A==, tableContent=null), ArticleFig(id=1327011135842267240, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, label=图1, caption=
本文框架图, figureFileSmall=PieiWSjIclD3y+uz1ydJng==, figureFileBig=LvNwWtG3mWG23wUf4tgR+A==, tableContent=null), ArticleFig(id=1327011136182005865, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, label=Figure 2, caption=
Diagram of research trends, figureFileSmall=R9r4G5DLPQarV9escNRvcA==, figureFileBig=37ytzq28hJpM8ZdwhVxA5A==, tableContent=null), ArticleFig(id=1327011136299446378, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, label=图2, caption=
研究趋势图, figureFileSmall=R9r4G5DLPQarV9escNRvcA==, figureFileBig=37ytzq28hJpM8ZdwhVxA5A==, tableContent=null), ArticleFig(id=1327011136362360939, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, label=Figure 3, caption=
Framework diagram of HOUYI, figureFileSmall=Bqns0Xf13Dkt//GajP5iZw==, figureFileBig=hg1srwM/qEJ73kjhWmdVEw==, tableContent=null), ArticleFig(id=1327011136433664108, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, label=图3, caption=
HOUYI框架图, figureFileSmall=Bqns0Xf13Dkt//GajP5iZw==, figureFileBig=hg1srwM/qEJ73kjhWmdVEw==, tableContent=null), ArticleFig(id=1327011136492384365, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, label=Figure 4, caption=
Framework diagram of Judge Deceiver attack, figureFileSmall=lZgX641hyv5iaMh5CzKCmQ==, figureFileBig=TwHspSzxDoNarhbRHpExIQ==, tableContent=null), ArticleFig(id=1327011136748236910, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, label=图4, caption=
Judge Deceiver攻击框架图, figureFileSmall=lZgX641hyv5iaMh5CzKCmQ==, figureFileBig=TwHspSzxDoNarhbRHpExIQ==, tableContent=null), ArticleFig(id=1327011136899231856, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, label=Figure 5, caption=
An example of indirect prompt injection, figureFileSmall=xw+dvD4k+qSlNqvp/6TLLA==, figureFileBig=n4COUoU042abkz0slv8dkQ==, tableContent=null), ArticleFig(id=1327011137016672369, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, label=图5, caption=
间接提示注入示例, figureFileSmall=xw+dvD4k+qSlNqvp/6TLLA==, figureFileBig=n4COUoU042abkz0slv8dkQ==, tableContent=null), ArticleFig(id=1327011137155084402, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, label=Figure 6, caption=
Framework diagram of Judge INJECAGENT attack, figureFileSmall=r6fRDrEvAvaBjFb3mbASdA==, figureFileBig=f4sjy7yjvVJtYeoUsfspVw==, tableContent=null), ArticleFig(id=1327011137293496435, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, label=图6, caption=
INJECAGENT攻击框架图, figureFileSmall=r6fRDrEvAvaBjFb3mbASdA==, figureFileBig=f4sjy7yjvVJtYeoUsfspVw==, tableContent=null), ArticleFig(id=1327011137519988853, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, label=Figure 7, caption=
Framework diagram of BadGPT attack, figureFileSmall=oWNDY2oJG6kDSI2PnTPvWA==, figureFileBig=pn8wm42OwQd5TEODp5ZkWQ==, tableContent=null), ArticleFig(id=1327011137696149622, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, label=图7, caption=
BadGPT攻击框架图, figureFileSmall=oWNDY2oJG6kDSI2PnTPvWA==, figureFileBig=pn8wm42OwQd5TEODp5ZkWQ==, tableContent=null), ArticleFig(id=1327011137880698999, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, label=Figure 8, caption=
Framework diagram of SmoothLLM method, figureFileSmall=dh0nwWRdQXGqgDldh0ktIA==, figureFileBig=MWAC5CYfduRgUlWOSOLg2A==, tableContent=null), ArticleFig(id=1327011137981362296, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, label=图8, caption=
SmoothLLM方法框架图, figureFileSmall=dh0nwWRdQXGqgDldh0ktIA==, figureFileBig=MWAC5CYfduRgUlWOSOLg2A==, tableContent=null), ArticleFig(id=1327011138098802809, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, label=Table 1, caption=
Summary of Prompt Injection Attacks, figureFileSmall=null, figureFileBig=null, tableContent=
| 分类 | 攻击方法 | 攻击原理 |
|---|
基于人工设计 的提示攻击 | 提示混淆 | 通过故意添加拼写错误或使用同义词来绕过模型自带的过滤器 |
| 虚拟化环境 | 通过提示构建虚拟场景以模拟指令的行为,为大语言模型提供 一个虚拟环境,从而降低其对生成内容负面影响的担忧 |
| 有效负载分割 | 将恶意有效负载分解为多个较小的单元,以规避防御机制 |
| SQL注入 | 在外部资源接口传递精心设计的问题,从而导致大语言模型生成恶意SQL查询 |
基于算法生成的 提示攻击 | 生成对抗性后缀 | 自动化算法生成对抗性后缀并附加到提示末尾,其形式对人类而言通常是无意义的 |
| 模拟攻击环境 | 通过本地聚合训练数据来精确模拟潜在的攻击环境,通过训练模型进一步优化对抗性文本 |
), ArticleFig(id=1327011138228826234, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, label=表1, caption=
提示注入攻击总结
, figureFileSmall=null, figureFileBig=null, tableContent=
| 分类 | 攻击方法 | 攻击原理 |
|---|
基于人工设计 的提示攻击 | 提示混淆 | 通过故意添加拼写错误或使用同义词来绕过模型自带的过滤器 |
| 虚拟化环境 | 通过提示构建虚拟场景以模拟指令的行为,为大语言模型提供 一个虚拟环境,从而降低其对生成内容负面影响的担忧 |
| 有效负载分割 | 将恶意有效负载分解为多个较小的单元,以规避防御机制 |
| SQL注入 | 在外部资源接口传递精心设计的问题,从而导致大语言模型生成恶意SQL查询 |
基于算法生成的 提示攻击 | 生成对抗性后缀 | 自动化算法生成对抗性后缀并附加到提示末尾,其形式对人类而言通常是无意义的 |
| 模拟攻击环境 | 通过本地聚合训练数据来精确模拟潜在的攻击环境,通过训练模型进一步优化对抗性文本 |
), ArticleFig(id=1327011138342072443, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, label=Table 2, caption=
Summary of Indirect Prompt Injection Attacks, figureFileSmall=null, figureFileBig=null, tableContent=
| 分类 | 攻击方法 | 攻击原理 |
|---|
| 面向单模态模型 | 嵌入外部资源 | 将恶意提示内容嵌入网页、PDF、TXT、代码辅助工具等外部资源中,让使用者在无意识中完成攻击. |
| 社会工程 | 攻击者使用社会工程提供的恶意提示,例如向毫无戒心的受害者提供指导或虚假承诺,然后受害者执行这些提示. |
| 面向多模态模型 | 面向白盒模型 | 使用对抗性扰动将指示和指令混合到图像和音频,扰动会引导模型输出攻击者选择的文本或指令. |
| 面向黑盒模型 | 不访问目标系统的参数或权重,仅通过攻击CLIP视觉编码器构建对抗性图形. |
), ArticleFig(id=1327011138501455996, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, label=表2, caption=
间接提示注入攻击总结
, figureFileSmall=null, figureFileBig=null, tableContent=
| 分类 | 攻击方法 | 攻击原理 |
|---|
| 面向单模态模型 | 嵌入外部资源 | 将恶意提示内容嵌入网页、PDF、TXT、代码辅助工具等外部资源中,让使用者在无意识中完成攻击. |
| 社会工程 | 攻击者使用社会工程提供的恶意提示,例如向毫无戒心的受害者提供指导或虚假承诺,然后受害者执行这些提示. |
| 面向多模态模型 | 面向白盒模型 | 使用对抗性扰动将指示和指令混合到图像和音频,扰动会引导模型输出攻击者选择的文本或指令. |
| 面向黑盒模型 | 不访问目标系统的参数或权重,仅通过攻击CLIP视觉编码器构建对抗性图形. |
), ArticleFig(id=1327011138665033853, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, label=Table 3, caption=
Summary of Jailbreak Attacks, figureFileSmall=null, figureFileBig=null, tableContent=
| 分类 | 攻击方法 | 攻击原理 |
|---|
| 基于人工设计 | 低资源编码 | 利用少量数据和特定编码策略,绕过大语言模型的安全训练,达成越狱目的. |
| 上下文学习 | 利用带标记示例的上下文演示,为大语言模型提供额外的上下文信息. |
| 虚拟化环境 | 通过虚拟化场景构建指令模拟环境,例如让大语言模型认为正处于 一个安全的试验场所,以降低其认为生成内容的潜在负面影响. |
| 图像与视觉集成扰动 | 通过对输入图像施加对抗性扰动,触发大语言模型生成有毒内容. |
| 基于算法生成 | 利用第三方大语言模型 | 利用辅助语言模型对越狱提示进行重新构造和优化,改进提示的语言流畅度、准确性和效果. |
), ArticleFig(id=1327011140401475710, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, label=表3, caption=
越狱攻击总结
, figureFileSmall=null, figureFileBig=null, tableContent=
| 分类 | 攻击方法 | 攻击原理 |
|---|
| 基于人工设计 | 低资源编码 | 利用少量数据和特定编码策略,绕过大语言模型的安全训练,达成越狱目的. |
| 上下文学习 | 利用带标记示例的上下文演示,为大语言模型提供额外的上下文信息. |
| 虚拟化环境 | 通过虚拟化场景构建指令模拟环境,例如让大语言模型认为正处于 一个安全的试验场所,以降低其认为生成内容的潜在负面影响. |
| 图像与视觉集成扰动 | 通过对输入图像施加对抗性扰动,触发大语言模型生成有毒内容. |
| 基于算法生成 | 利用第三方大语言模型 | 利用辅助语言模型对越狱提示进行重新构造和优化,改进提示的语言流畅度、准确性和效果. |
), ArticleFig(id=1327011140766380159, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, label=Table 4, caption=
Summary of Backdoor Attacks, figureFileSmall=null, figureFileBig=null, tableContent=
| 攻击方法 | 攻击原理 |
|---|
| 奖励模型 | 利用毒化数据集在微调过程中修改模型的奖励偏好,攻击者通过在提示符中注入特殊的触发器激活后门. |
| 木马适配器 | 制作恶意木马适配器,传播敌对偏好的叙述,向特定群体传播个性化的虚假信息. |
| 思维链 | 恶意利用大语言模型集成应用中的第三方提示工程服务,在其中嵌入后门触发器. |
| 多目标优化 | 通过感知相似性约束、多任务目标优化和模型交替训练等技术,使后门图像与原始图像难以区分. |
), ArticleFig(id=1327011140883820672, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, label=表4, caption=
后门攻击总结
, figureFileSmall=null, figureFileBig=null, tableContent=
| 攻击方法 | 攻击原理 |
|---|
| 奖励模型 | 利用毒化数据集在微调过程中修改模型的奖励偏好,攻击者通过在提示符中注入特殊的触发器激活后门. |
| 木马适配器 | 制作恶意木马适配器,传播敌对偏好的叙述,向特定群体传播个性化的虚假信息. |
| 思维链 | 恶意利用大语言模型集成应用中的第三方提示工程服务,在其中嵌入后门触发器. |
| 多目标优化 | 通过感知相似性约束、多任务目标优化和模型交替训练等技术,使后门图像与原始图像难以区分. |
), ArticleFig(id=1327011141022232706, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, label=Table 5, caption=
Comparison of Adversarial Attack Methods on Large Language Models, figureFileSmall=null, figureFileBig=null, tableContent=
| 攻击方法 | 攻击路径 | 优势 | 劣势 |
|---|
| 提示注入 | 通过恶意提示诱导模型生成攻击者想要的输出 | 适用于黑盒模型,无需依赖模型内部信息 | 扩展性有限,移植性差,易被检测识别 |
| 间接提示注入 | 在外部媒介中嵌入恶意指令 | 隐蔽性高,难以检测和防范 | 攻击效果严重依赖外部资源 |
| 越狱攻击 | 绕过模型对齐机制 | 适用于黑盒模型 | 过于模板化,易于被识别 |
| 后门攻击 | 在模型内部植入后门,使其在满足特定触发条件时激活 | 隐蔽性高,通常情况下难以察觉 | 需要充分了解模型结构和训练过程 |
), ArticleFig(id=1327011141122896003, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, label=表5, caption=
大语言模型对抗性攻击方法对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 攻击方法 | 攻击路径 | 优势 | 劣势 |
|---|
| 提示注入 | 通过恶意提示诱导模型生成攻击者想要的输出 | 适用于黑盒模型,无需依赖模型内部信息 | 扩展性有限,移植性差,易被检测识别 |
| 间接提示注入 | 在外部媒介中嵌入恶意指令 | 隐蔽性高,难以检测和防范 | 攻击效果严重依赖外部资源 |
| 越狱攻击 | 绕过模型对齐机制 | 适用于黑盒模型 | 过于模板化,易于被识别 |
| 后门攻击 | 在模型内部植入后门,使其在满足特定触发条件时激活 | 隐蔽性高,通常情况下难以察觉 | 需要充分了解模型结构和训练过程 |
), ArticleFig(id=1327011141240336516, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=EN, label=Table 6, caption=
Comparison of Defense Methods for Large Language Models, figureFileSmall=null, figureFileBig=null, tableContent=
| 防御方法 | 技术路径 | 优势 | 劣势 |
|---|
| 提示词审查 | 过滤敏感词汇或指令 | 简单有效,适用模型类型广 | 易产生假阳性,防御攻击类型有限 |
| 提示词变换 | 修改提示词表述方式,避免触发不良行为 | 防御广泛的攻击类型 | 模型性能下降 |
| 对抗性训练 | 将对抗样本融入训练数据中 | 提高模型自身对对抗攻击的鲁棒性 | 训练成本高,可能降低模型的泛化能力 |
| 激发模型自身能力的防御 | 利用模型已有的能力进行防御 | 无需额外训练,利用模型机理 | 难以评估防御效果 |
), ArticleFig(id=1327011141353582726, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327011123464876051, language=CN, label=表6, caption=
大语言模型防御方法对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 防御方法 | 技术路径 | 优势 | 劣势 |
|---|
| 提示词审查 | 过滤敏感词汇或指令 | 简单有效,适用模型类型广 | 易产生假阳性,防御攻击类型有限 |
| 提示词变换 | 修改提示词表述方式,避免触发不良行为 | 防御广泛的攻击类型 | 模型性能下降 |
| 对抗性训练 | 将对抗样本融入训练数据中 | 提高模型自身对对抗攻击的鲁棒性 | 训练成本高,可能降低模型的泛化能力 |
| 激发模型自身能力的防御 | 利用模型已有的能力进行防御 | 无需额外训练,利用模型机理 | 难以评估防御效果 |
)], 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/issn1000-1239.202440630, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202440630, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202440630, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202440630, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1740758400000, fullTextJson=null, articleText=null, reference=null)