Article(id=1327018598960313188, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327018536993665336, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202440327, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1716220800000, receivedDateStr=2024-05-21, revisedDate=1734624000000, revisedDateStr=2024-12-20, acceptedDate=1736352000000, acceptedDateStr=2025-01-09, onlineDate=1794315488804, onlineDateStr=2026-11-10, pubDate=1753977600000, pubDateStr=2025-08-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794315488804, onlineIssueDateStr=2026-11-10, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794315488804, creator=13701087609, updateTime=1794315488804, updator=13701087609, issue=Issue{id=1327018536993665336, tenantId=1146029695717560320, journalId=1324759914146529478, year='2025', volume='62', issue='8', pageStart='1833', pageEnd='2124', issueExtLink='null', onlineDate='null', pubDate='1753977600000', pubDateStr='2025-08-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794315474031, creator='13701087609', updateTime=1794376881014, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1327276097470837643, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327018536993665336, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1327276097470837644, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327018536993665336, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=2019, endPage=2039, ext={EN=ArticleExt(id=1327018599149056869, articleId=1327018598960313188, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Security of Deep Learning Model Supply Chains: A Survey, columnId=1325493671541474142, journalTitle=Journal of Computer Research and Development, columnName=Network and Information Security, runingTitle=null, highlight=null, articleAbstract=
Pre-trained models have mitigated the challenges posed by extensive training data and computational resources, and also give birth to the new paradigm of model development and application, which we refer to as model supply chain. In this framework, a pre-trained model is uploaded by its publisher and subsequently transferred, compressed, and deployed by secondary developers to meet various application needs. This emerging model supply chain introduces additional stages and multiple elements, inevitably leading to security concerns and privacy risks. Despite the widespread adoption of model supply chains, there is currently a lack of systematic review of security threats in them. To address this research gap, we provide a comprehensive overview of the deep learning model supply chain, introducing its concept and fundamental structure. We conduct an in-depth analysis of vulnerabilities at various stages of the model’s lifecycle, including design, development, deployment, and usage. Furthermore, we compare and summarize prevalent attack methods, alongside introducing corresponding security protection strategies. To assist readers in effectively utilizing pre-trained models, we review and compare publicly available model repositories. Finally, we discuss potential future research avenues in areas such as security checks, real-time detection, and problem tracing. This review aims to offer insights for safer and more reliable development and use of pre-training models. For the benefit of ongoing research, related papers and open-source codes of the methods discussed are accessible at website: https://github.com/Dipsy0830/DNN-supply-chain-survey.
, authors=Ruoxi Chen
1, Jinyin Chen
2, 1, *, Haibin Zheng
2, 1, Xueyan Yang
1, Shouling Ji
3, Tieming Chen
4, authorsList=Ruoxi Chen, Jinyin Chen, Haibin Zheng, Xueyan Yang, Shouling Ji, Tieming Chen, authorCompany=null, correspAuthors=Jinyin Chen, authorNote=
born in 1998. PhD candidate. Student candidate of CCF. Her main research interests include deep learning and artificial intelligence security
born in 1982. PhD, professor. Member of CCF. Her main research interests include artificial intelligence security, graph data mining, and evolutionary computing
born in 1995. PhD, lecturer. Member of CCF. His main research interests include deep learning, artificial intelligence security, and fairness algorithm
born in 2003. Undergraduate student. Her main research interests include deep learning and artificial intelligence security
born in 1986. PhD. Senior member of CCF. ZJU 100-Young Professor in the College of Computer Science and Technology at Zhejiang University. His current research interests include data-driven security and privacy, AI security, and big data analytics
born in 1978. PhD, professor. His main research interest includes network information 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=1327018602806489978, articleId=1327018598960313188, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=深度学习模型供应链的安全性综述, columnId=1325493672690713440, journalTitle=计算机研究与发展, columnName=网络与信息安全, runingTitle=null, highlight=null, articleAbstract=
预训练模型缓解了训练数据和算力受限的问题,也催生了模型开发和应用的新范式——深度学习模型供应链. 在这一供应链中,预训练模型由原始发布者上传,并经二次开发者进行必要的迁移、压缩与部署,以适应不同的应用需求. 然而,这一过程引入了新的环节和多元要素,随之产生了数据泄露和计算安全等风险. 尽管深度学习模型供应链已被广泛采纳,目前对于其安全性威胁的系统性研究仍然不足. 针对这一研究空白,概括了深度学习模型供应链的概念及其基本框架,调研了相关的研究工作. 依据模型生命周期的不同阶段,详细分析了设计、二次开发、部署和使用各环节的安全脆弱点,对可能遭遇的安全性攻击手段进行了系统的梳理、比较和总结,并探讨了相应的防护策略. 为了帮助读者更好地使用预训练模型,对现有预训练模型仓库进行了比较. 最后,基于目前深度学习模型供应链所面临的挑战,从安全性审查、实时检测和问题溯源等不同角度分析和讨论了未来可能的研究发展方向,为更安全可靠地开发和使用预训练模型提供了思路. 论文涉及的方法和相关代码归纳整理在网址:https://github.com/Dipsy0830/DNN-supply-chain-survey,方便研究人员下载使用.
, authors=陈若曦
1, 陈晋音
2, 1, *, 郑海斌
2, 1, 阳雪燕
1, 纪守领
3, 陈铁明
4, authorsList=陈若曦, 陈晋音, 郑海斌, 阳雪燕, 纪守领, 陈铁明, authorCompany=null, correspAuthors=陈晋音, authorNote=
 |
1998年生. 博士研究生. CCF学生会员. 主要研究方向为深度学习、人工智能安全 |
 |
1982年生. 博士,教授,CCF会员. 主要研究方向为人工智能安全、图数据挖掘、进化计算 |
 |
1995年生. 博士,讲师. CCF会员. 主要研究方向为深度学习、人工智能安全、公平性算法 |
 |
2003年生. 本科生. 主要研究方向为深度学习、人工智能安全 |
 |
1986年生. 博士,CCF高级会员,浙江大学“百人计划”研究员. 主要研究方向为数据驱动安全和隐私、AI安全、大数据分析 |
 |
1978年生. 博士,教授. 主要研究方向为网络信息安全 |
, 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=5swmcCPG71Tf2nPB0FsAtA==, magXml=UU9CTQewEUZjscFxu6DWaQ==, pdfUrl=null, pdf=aT96Z98T5OosdciXLV9AnQ==, pdfFileSize=1288327, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=jK6VLcM1ZQ7DxysH3+9X7w==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=CqY4iURF3BJ6YVsJ7TQlsQ==, mapNumber=null, fund=null)}, authors=[Author(id=1327018603477578632, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=2112003149@zjut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018603548881802, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, authorId=1327018603477578632, language=EN, stringName=Ruoxi Chen, firstName=Ruoxi, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1College of Information Engineering, Zhejiang University of Technology University, Hangzhou 310023, bio={"content":"
born in 1998. PhD candidate. Student candidate of CCF. Her main research interests include deep learning and artificial intelligence security
"}, bioImg=null, bioContent=
born in 1998. PhD candidate. Student candidate of CCF. Her main research interests include deep learning and artificial intelligence security
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018603632767883, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, authorId=1327018603477578632, language=CN, stringName=陈若曦, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1浙江工业大学信息工程学院 杭州 310023, bio={"img":"MwyfPwdh0dn43BSSenn7qg==","content":"
1998年生. 博士研究生. CCF学生会员. 主要研究方向为深度学习、人工智能安全
"}, bioImg=MwyfPwdh0dn43BSSenn7qg==, bioContent=
1998年生. 博士研究生. CCF学生会员. 主要研究方向为深度学习、人工智能安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018603062342523, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, xref=1, ext=[AuthorCompanyExt(id=1327018603074925436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603062342523, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Information Engineering, Zhejiang University of Technology University, Hangzhou 310023), AuthorCompanyExt(id=1327018603087508349, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603062342523, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1浙江工业大学信息工程学院 杭州 310023)])]), Author(id=1327018603712459661, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=chenjinyin@zjut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1327018603787957136, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, authorId=1327018603712459661, language=EN, stringName=Jinyin Chen, firstName=Jinyin, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, 1, *, address=
2Institute of Cyberspace Security, Zhejiang University of Technology University, Hangzhou 310023
1College of Information Engineering, Zhejiang University of Technology University, Hangzhou 310023, bio={"content":"
born in 1982. PhD, professor. Member of CCF. Her main research interests include artificial intelligence security, graph data mining, and evolutionary computing
"}, bioImg=null, bioContent=
born in 1982. PhD, professor. Member of CCF. Her main research interests include artificial intelligence security, graph data mining, and evolutionary computing
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018603846677393, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, authorId=1327018603712459661, language=CN, stringName=陈晋音, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, 1, *, address=
2浙江工业大学网络空间安全研究院 杭州 310023
1浙江工业大学信息工程学院 杭州 310023, bio={"img":"igoBFc+Lfz6EZckBP8MJ2g==","content":"
1982年生. 博士,教授,CCF会员. 主要研究方向为人工智能安全、图数据挖掘、进化计算
"}, bioImg=igoBFc+Lfz6EZckBP8MJ2g==, bioContent=
1982年生. 博士,教授,CCF会员. 主要研究方向为人工智能安全、图数据挖掘、进化计算
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018603200754558, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, xref=2, ext=[AuthorCompanyExt(id=1327018603209143167, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603200754558, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Institute of Cyberspace Security, Zhejiang University of Technology University, Hangzhou 310023), AuthorCompanyExt(id=1327018603217531776, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603200754558, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2浙江工业大学网络空间安全研究院 杭州 310023)]), AuthorCompany(id=1327018603062342523, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, xref=1, ext=[AuthorCompanyExt(id=1327018603074925436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603062342523, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Information Engineering, Zhejiang University of Technology University, Hangzhou 310023), AuthorCompanyExt(id=1327018603087508349, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603062342523, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1浙江工业大学信息工程学院 杭州 310023)])]), Author(id=1327018603909591955, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=1327018603976700822, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, authorId=1327018603909591955, language=EN, stringName=Haibin Zheng, firstName=Haibin, middleName=null, lastName=Zheng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, 1, address=
2Institute of Cyberspace Security, Zhejiang University of Technology University, Hangzhou 310023
1College of Information Engineering, Zhejiang University of Technology University, Hangzhou 310023, bio={"content":"
born in 1995. PhD, lecturer. Member of CCF. His main research interests include deep learning, artificial intelligence security, and fairness algorithm
"}, bioImg=null, bioContent=
born in 1995. PhD, lecturer. Member of CCF. His main research interests include deep learning, artificial intelligence security, and fairness algorithm
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018604039615383, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, authorId=1327018603909591955, language=CN, stringName=郑海斌, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, 1, address=
2浙江工业大学网络空间安全研究院 杭州 310023
1浙江工业大学信息工程学院 杭州 310023, bio={"img":"t/6YsjtYHjM5Ouxx2q2gyg==","content":"
1995年生. 博士,讲师. CCF会员. 主要研究方向为深度学习、人工智能安全、公平性算法
"}, bioImg=t/6YsjtYHjM5Ouxx2q2gyg==, bioContent=
1995年生. 博士,讲师. CCF会员. 主要研究方向为深度学习、人工智能安全、公平性算法
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018603200754558, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, xref=2, ext=[AuthorCompanyExt(id=1327018603209143167, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603200754558, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Institute of Cyberspace Security, Zhejiang University of Technology University, Hangzhou 310023), AuthorCompanyExt(id=1327018603217531776, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603200754558, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2浙江工业大学网络空间安全研究院 杭州 310023)]), AuthorCompany(id=1327018603062342523, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, xref=1, ext=[AuthorCompanyExt(id=1327018603074925436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603062342523, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Information Engineering, Zhejiang University of Technology University, Hangzhou 310023), AuthorCompanyExt(id=1327018603087508349, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603062342523, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1浙江工业大学信息工程学院 杭州 310023)])]), Author(id=1327018604106724249, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=1327018604182221723, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, authorId=1327018604106724249, language=EN, stringName=Xueyan Yang, firstName=Xueyan, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1College of Information Engineering, Zhejiang University of Technology University, Hangzhou 310023, bio={"content":"
born in 2003. Undergraduate student. Her main research interests include deep learning and artificial intelligence security
"}, bioImg=null, bioContent=
born in 2003. Undergraduate student. Her main research interests include deep learning and artificial intelligence security
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018604253524892, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, authorId=1327018604106724249, language=CN, stringName=阳雪燕, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1浙江工业大学信息工程学院 杭州 310023, bio={"img":"wzqkKWKZz5Z3JSE4LPMc2A==","content":"
2003年生. 本科生. 主要研究方向为深度学习、人工智能安全
"}, bioImg=wzqkKWKZz5Z3JSE4LPMc2A==, bioContent=
2003年生. 本科生. 主要研究方向为深度学习、人工智能安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018603062342523, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, xref=1, ext=[AuthorCompanyExt(id=1327018603074925436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603062342523, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Information Engineering, Zhejiang University of Technology University, Hangzhou 310023), AuthorCompanyExt(id=1327018603087508349, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603062342523, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1浙江工业大学信息工程学院 杭州 310023)])]), Author(id=1327018604324828062, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=1327018604396131232, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, authorId=1327018604324828062, language=EN, stringName=Shouling Ji, firstName=Shouling, middleName=null, lastName=Ji, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
3, address=
3College of Computer Science and Technology, Zhejiang University, Hangzhou 310007, bio={"content":"
born in 1986. PhD. Senior member of CCF. ZJU 100-Young Professor in the College of Computer Science and Technology at Zhejiang University. His current research interests include data-driven security and privacy, AI security, and big data analytics
"}, bioImg=null, bioContent=
born in 1986. PhD. Senior member of CCF. ZJU 100-Young Professor in the College of Computer Science and Technology at Zhejiang University. His current research interests include data-driven security and privacy, AI security, and big data analytics
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018604505183137, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, authorId=1327018604324828062, language=CN, stringName=纪守领, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
3, address=
3浙江大学计算机科学与技术学院 杭州 310007, bio={"img":"glY+M3Hu59kvrbzckNA2bw==","content":"
1986年生. 博士,CCF高级会员,浙江大学“百人计划”研究员. 主要研究方向为数据驱动安全和隐私、AI安全、大数据分析
"}, bioImg=glY+M3Hu59kvrbzckNA2bw==, bioContent=
1986年生. 博士,CCF高级会员,浙江大学“百人计划”研究员. 主要研究方向为数据驱动安全和隐私、AI安全、大数据分析
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018603293029249, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, xref=3, ext=[AuthorCompanyExt(id=1327018603305612162, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603293029249, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3College of Computer Science and Technology, Zhejiang University, Hangzhou 310007), AuthorCompanyExt(id=1327018603309806467, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603293029249, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3浙江大学计算机科学与技术学院 杭州 310007)])]), Author(id=1327018604563903395, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018604635206565, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, authorId=1327018604563903395, language=EN, stringName=Tieming Chen, firstName=Tieming, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
4, address=
4College of Computer Science and Technology, Zhejiang University of Technology University, Hangzhou 310023, bio={"content":"
born in 1978. PhD, professor. His main research interest includes network information security
"}, bioImg=null, bioContent=
born in 1978. PhD, professor. His main research interest includes network information security
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018604693926822, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, authorId=1327018604563903395, language=CN, stringName=陈铁明, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
4, address=
4浙江工业大学计算机科学与技术学院 杭州 310023, bio={"img":"9z5KxejXm+v/QXZI8F7OhA==","content":"
1978年生. 博士,教授. 主要研究方向为网络信息安全
"}, bioImg=9z5KxejXm+v/QXZI8F7OhA==, bioContent=
1978年生. 博士,教授. 主要研究方向为网络信息安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018603381109636, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, xref=4, ext=[AuthorCompanyExt(id=1327018603389498245, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603381109636, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4College of Computer Science and Technology, Zhejiang University of Technology University, Hangzhou 310023), AuthorCompanyExt(id=1327018603397886854, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603381109636, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4浙江工业大学计算机科学与技术学院 杭州 310023)])])], keywords=[Keyword(id=1327018604777812903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=EN, orderNo=1, keyword=model supply chain), Keyword(id=1327018604878476200, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=EN, orderNo=2, keyword=pre-trained models), Keyword(id=1327018604953973673, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=EN, orderNo=3, keyword=security threats), Keyword(id=1327018605033665450, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=EN, orderNo=4, keyword=security and privacy), Keyword(id=1327018605104968619, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=EN, orderNo=5, keyword=deep neural networks), Keyword(id=1327018606883353516, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=EN, orderNo=6, keyword=deep learning), Keyword(id=1327018606958850989, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=CN, orderNo=1, keyword=模型供应链), Keyword(id=1327018607025959854, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=CN, orderNo=2, keyword=预训练模型), Keyword(id=1327018607093068719, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=CN, orderNo=3, keyword=安全风险), Keyword(id=1327018607160177584, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=CN, orderNo=4, keyword=安全与隐私), Keyword(id=1327018607218897841, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=CN, orderNo=5, keyword=深度神经网络), Keyword(id=1327018607286006706, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=CN, orderNo=6, keyword=深度学习)], refs=[Reference(id=1327018612327560133, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Hugging Face. Hugging Face―The AI community building the future[EB/OL]. (2016-03-01)[2022-03-21]. https://huggingface.co/, articleTitle=null, refAbstract=null), Reference(id=1327018612465972166, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Yu Koh J. Model Zoo―Deep learning code and pretrained models[EB/OL]. (2018-06-14)[2023-03-15]. https://modelzoo.co/, articleTitle=null, refAbstract=null), Reference(id=1327018612558246855, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Qiu Xipeng, Sun Tianxiang, Xu Yige, et al. Pre-trained models for natural language processing: A survey[J]. Science China Technological Sciences, 2020, 63(10): 1872−1897, articleTitle=null, refAbstract=null), Reference(id=1327018612671493064, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint, arXiv: 1409.1556, 2014, articleTitle=null, refAbstract=null), Reference(id=1327018612742796233, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Baracaldo N, Oprea A. Machine learning security and privacy[J]. IEEE Security & Privacy, 2022, 20(5): 11−13, articleTitle=null, refAbstract=null), Reference(id=1327018612805710794, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Liu Ximeng, Xie Lehui, Wang Yaopeng, et al. Privacy and security issues in deep learning: A survey[J]. IEEE Access, 2020, 9: 4566−4593, articleTitle=null, refAbstract=null), Reference(id=1327018612881208267, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=Xue Mingfu, Yuan Chengxiang, Wu Heyi, et al. Machine learning security: Threats, countermeasures, and evaluations[J]. IEEE Access, 2020, 8: 74720−74742, articleTitle=null, refAbstract=null), Reference(id=1327018612960900044, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Kenton J D M W C, Toutanova L K. BERT: Pre-training of deep bidirectional transformers for language understanding[C]//Proc of the 17th NAACL-HLT. Stroudsburg, PA: ACL, 2019: 4171−4186, articleTitle=null, refAbstract=null), Reference(id=1327018613036397517, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: Transformers for image recognition at scale[J]. arXiv preprint, arXiv: 2010.11929, 2020, articleTitle=null, refAbstract=null), Reference(id=1327018613095117774, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Radford A, Kim J W, Hallacy C, et al. Learning transferable visual models from natural language supervision[C]//Proc of the 18th Int Conf on Machine Learning. New York: PMLR, 2021: 8748−8763, articleTitle=null, refAbstract=null), Reference(id=1327018613162226639, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Haotian, Li Chunyuan, Wu Qingyang, et al. Visual instruction tuning[J]. arXiv preprint, arXiv: 2304.08485, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018613229335504, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Rombach R, Blattmann A, Lorenz D, et al. High-resolution image synthesis with latent diffusion models[C]//Proc of the 39th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 10684−10695, articleTitle=null, refAbstract=null), Reference(id=1327018613309027281, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Cruz Jr G V, Du Yunshu, Taylor M E. Pre-training neural networks with human demonstrations for deep reinforcement learning[J]. arXiv preprint, arXiv: 1709.04083, 2017, articleTitle=null, refAbstract=null), Reference(id=1327018613367747538, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Wenxin, Synovic N, Sethi R, et al. An empirical study of artifacts and security risks in the pre-trained model supply chain[C]//Proc of the 1st ACM Workshop on Software Supply Chain Offensive Research and Ecosystem Defenses. New York: ACM, 2022: 105−114, articleTitle=null, refAbstract=null), Reference(id=1327018613439050707, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=TensorFlow. TensorFlow Hub[EB/OL]. (2018-03-01)[2023-03-18]. https://www.tensorflow.org/hub, articleTitle=null, refAbstract=null), Reference(id=1327018613506159572, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=NVIDIA. NVIDIA NGC: AI development catalog[EB/OL]. (2017-10-01)[2023-03-21]. https://catalog.ngc, articleTitle=null, refAbstract=null), Reference(id=1327018613569074133, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Russakovsky O, Deng Jia, Su Hao, et al. ImageNet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015, 115: 211−252, articleTitle=null, refAbstract=null), Reference(id=1327018613631988694, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition[C]//Proc of the 29th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2016: 770−778, articleTitle=null, refAbstract=null), Reference(id=1327018613694903255, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=He Kaiming, Girshick R, Dollár P. Rethinking ImageNet pre-training[C]//Proc of the 32nd IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 4918−4927, articleTitle=null, refAbstract=null), Reference(id=1327018613770400728, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Jajal P, Jiang Wenxin, Tewari A, et al. Analysis of failures and risks in deep learning model converters: A case study in the ONNX ecosystem[J]. arXiv preprint, arXiv: 2303.17708, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018613845898201, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Choudhary T, Mishra V, Goswami A, et al. A comprehensive survey on model compression and acceleration[J]. Artificial Intelligence Review, 2020, 53: 5113−5155, articleTitle=null, refAbstract=null), Reference(id=1327018613913007066, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Krishnamoorthi R. Quantizing deep convolutional networks for efficient inference: A whitepaper[J]. arXiv preprint, arXiv: 1806.08342, 2018, articleTitle=null, refAbstract=null), Reference(id=1327018613980115931, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Dong Xin, Chen Shangyu, Pan S. Learning to prune deep neural networks via layer-wise optimal brain surgeon[J]. Advances in Neural Information Processing Systems, 2017, 30(1): 4857−4867, articleTitle=null, refAbstract=null), Reference(id=1327018614043030492, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=高晗,田育龙,许封元,等. 深度学习模型压缩与加速综述[J]. 软件学报,2021,32(1):68−92, articleTitle=null, refAbstract=null), Reference(id=1327018615741723614, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Gao Han, Tian Yulong, Xu Fengyuan, et al. Survey of deep learning model compression and acceleration[J]. Journal of Software, 2021, 32(1): 68−92 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327018615808832479, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network[J]. arXiv preprint, arXiv: 1503.02531, 2015, articleTitle=null, refAbstract=null), Reference(id=1327018615880135648, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Dube P, Bhattacharjee B, Huo Siyu, et al. Automatic labeling of data for transfer learning suggestion[C/OL]//Proc of the 32nd IEEE/CVF Conf on Computer Vision and Pattern Recognition. 2019[2023-05-06]. https://openreview.net/forum?id=rkxJgoRN_V, articleTitle=null, refAbstract=null), Reference(id=1327018615976604641, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Hugging Face[EB/OL]. (2016-03-01)[2022-03-21]. https://huggingface.co/datasets/beans, articleTitle=null, refAbstract=null), Reference(id=1327018616043713506, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Schelter S, Biessmann F, Januschowski T, et al. On challenges in machine learning model management[J/OL]. IEEE Data Engineering Bulletin. 2015[2023-05-02]. https://www.amazon.science/publications/on-challenges-in-machine-learning-model-management, articleTitle=null, refAbstract=null), Reference(id=1327018616123405283, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Shen Lujia, Ji Shouling, Zhang Xuhong, et al. Backdoor pre-trained models can transfer to all[C]//Proc of the 28th ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2021: 3141−3158, articleTitle=null, refAbstract=null), Reference(id=1327018616215679972, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=纪守领,杜天宇,李进锋,等. 机器学习模型安全与隐私研究综述[J]. 软件学报,2021,32(1):41−67, articleTitle=null, refAbstract=null), Reference(id=1327018616295371749, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Ji Shouling, Du Tianyu, Li Jinfeng, et al. Security and privacy of machine learning models: A survey[J]. Journal of Software, 2021, 32(1): 41−67 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327018616379257830, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Wenxin, Synovic N, Hyatt M, et al. An empirical study of pre-trained model reuse in the hugging face deep learning model registry[J]. arXiv preprint, arXiv: 2303.02552, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018616446366695, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Wenxin, Banna V, Vivek N, et al. Challenges and practices of deep learning model reengineering: A case study on computer vision[J]. arXiv preprint, arXiv: 2303.07476, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018616513475560, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Zeyan, Li Fengjun, Li Zhu, et al. LoneNeuron: A highly-effective feature-domain neural trojan using invisible and polymorphic watermarks[C]//Proc of the 29th ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2022: 2129−2143, articleTitle=null, refAbstract=null), Reference(id=1327018616601555945, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Kurita K, Michel P, Neubig G. Weight poisoning attacks on pretrained models[C]//Proc of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2020: 2793−2806, articleTitle=null, refAbstract=null), Reference(id=1327018616689636330, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Linyang, Song Demin, Li Xiaonan, et al. Backdoor attacks on pre-trained models by layerwise weight poisoning[C]//Proc of the 58th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2021: 3023−3032, articleTitle=null, refAbstract=null), Reference(id=1327018616790299627, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Xinyang, Zhang Zheng, Ji Shouling, et al. Trojaning language models for fun and profit[C]//Proc of the 6th IEEE European Symp on Security and Privacy (EuroS&P). Piscataway, NJ: IEEE, 2021: 179−197, articleTitle=null, refAbstract=null), Reference(id=1327018616911934444, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Cai Xiangrui, Xu Haidong, Xu Sihan, et al. BadPrompt: Backdoor attacks on continuous prompts[J]. Advances in Neural Information Processing Systems, 2022, 35(1): 37068−37080, articleTitle=null, refAbstract=null), Reference(id=1327018616995820525, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Grill J B, Strub F, Altché F, et al. Bootstrap your own latent—A new approach to self-supervised learning[J]. Advances in Neural Information Processing Systems, 2020, 33(1): 21271−21284, articleTitle=null, refAbstract=null), Reference(id=1327018617062929390, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Jia Jinyuan, Liu Yupei, Gong Zhengqiang. BadEncoder: Backdoor attacks to pre-trained encoders in self-supervised learning[C]//Proc of the 43rd IEEE Symp on Security and Privacy (SP). Piscataway, NJ: IEEE, 2022: 2043−2059, articleTitle=null, refAbstract=null), Reference(id=1327018617130038255, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Hongbin, Jia Jinyuan, Gong Zhengqiang. PoisonedEncoder: Poisoning the unlabeled pre-training data in contrastive learning[C]//Proc of the 31st USENIX Security Symp (USENIX Security 22). Berkeley, CA: USENIX Association, 2022: 3629−3645, articleTitle=null, refAbstract=null), Reference(id=1327018617197147120, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Ting, Kornblith S, Norouzi M, et al. A simple framework for contrastive learning of visual representations[C]//Proc of the 37th Int Conf on Machine Learning. New York: PMLR, 2020: 1597−1607, articleTitle=null, refAbstract=null), Reference(id=1327018617289421809, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Jinghuai, Liu Hongbin, Jia Jinyuan, et al. CorruptEncoder: Data poisoning based backdoor attacks to contrastive learning[J]. arXiv preprint, arXiv: 2211.08229, 2022, articleTitle=null, refAbstract=null), Reference(id=1327018617377502194, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Ji Yujie, Zhang Xinyang, Ji Shouling, et al. Model-reuse attacks on deep learning systems[C]//Proc of the 25th ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2018: 349−363, articleTitle=null, refAbstract=null), Reference(id=1327018617452999667, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Kangjie, Meng Yuxian, Sun Xiaofei, et al. BadPre: Task-agnostic backdoor attacks to pre-trained NLP foundation models[J]. arXiv preprint, arXiv: 2110.02467, 2021, articleTitle=null, refAbstract=null), Reference(id=1327018617524302836, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Zhengyan, Xiao Guangxuan, Li Yongwei, et al. Red alarm for pre-trained models: Universal vulnerability to neuron-level backdoor attacks[J]. Machine Intelligence Research, 2023, 20(2): 180−193, articleTitle=null, refAbstract=null), Reference(id=1327018617587217397, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Lv Peizhuo, Yue Chang, Liang Ruigang, et al. A data-free backdoor injection approach in neural networks[C]//Proc of the 32nd USENIX Security Symp (USENIX Security 23). Berkeley, CA: USENIX Association, 2023: 2671−2688, articleTitle=null, refAbstract=null), Reference(id=1327018617658520566, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Mei Kai, Li Zheng, Wang Zhenting, et al. NOTABLE: Transferable backdoor attacks against prompt-based NLP models[C]//Proc of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2023: 15551−15565, articleTitle=null, refAbstract=null), Reference(id=1327018617738212343, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Du Wei, Li Peixuan, Li Boqun, et al. UOR: Universal backdoor attacks on pre-trained language models[J]. arXiv preprint, arXiv: 2305.09574, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018617809515512, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Hao, Guo Shangwei, He Jialiang, et al. Model supply chain poisoning: Backdooring pre-trained models via embedding indistinguishability[J]. arXiv preprint, arXiv: 2401.15883, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018617876624377, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Yujun, Zhuo Terry Yue, Xu Qiongkai, et al. Training-free lexical backdoor attacks on language models[C]//Proc of the 32nd ACM Web Conf 2023. New York: ACM, 2023: 2198−2208, articleTitle=null, refAbstract=null), Reference(id=1327018617939538938, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Yue, Wang Weishi, Joty S, et al. CodeT5: Identifier-aware unified pre-trained encoder-decoder models for code understanding and generation[C]//Proc of the 36th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2021: 8696−8708, articleTitle=null, refAbstract=null), Reference(id=1327018618027619323, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Yanzhou, Liu Shangqing, Chen Kangjie, et al. Multi-target backdoor attacks for code pre-trained models[J]. arXiv preprint, arXiv: 2306.08350, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018618098922492, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Bolun, Yao Yuanshun , Viswanath B, et al. With great training comes great vulnerability: Practical attacks against transfer learning[C]//Proc of the 27th USENIX Security Symp (USENIX Security 18). Berkeley, CA: USENIX Association, 2018: 1281−1297, articleTitle=null, refAbstract=null), Reference(id=1327018618178614269, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=Yao Yuanshun, Li Huiying, Zheng Haitao, et al. Latent backdoor attacks on deep neural networks[C]//Proc of the 26th ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2019: 2041−2055, articleTitle=null, refAbstract=null), Reference(id=1327018618245723134, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=55, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Shuo, Nepal S, Rudolph C, et al. Backdoor attacks against transfer learning with pre-trained deep learning models[J]. IEEE Transactions on Services Computing, 2020, 15(3): 1526−1539, articleTitle=null, refAbstract=null), Reference(id=1327018618308637695, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=56, rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Wenbo, Zhang Tianwei, Qiu H, et al. Incremental learning, incremental backdoor threats[J]. IEEE Transactions on Dependable and Secure Computing, 2022, 21(2): 559−572, articleTitle=null, refAbstract=null), Reference(id=1327018618400912384, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=57, rfOrder=58, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Zhizhong, Hoiem D. Learning without forgetting[J]. IEEE Transactions on Pattern Analysis And Machine Intelligence, 2017, 40(12): 2935−2947, articleTitle=null, refAbstract=null), Reference(id=1327018618488991744, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=58, rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=Ban Yuanhao, Dong Yinpeng. Pre-trained adversarial perturbations[J]. Advances in Neural Information Processing Systems, 2022, 35(1): 1196−1209, articleTitle=null, refAbstract=null), Reference(id=1327018618564489217, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=59, rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=Lester B, Al-Rfou R, Constant N. The power of scale for parameter-efficient prompt tuning[C]//Proc of the 26th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2021: 3045−3059, articleTitle=null, refAbstract=null), Reference(id=1327018620242210818, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=60, rfOrder=61, authorNames=null, journalName=null, refType=null, unstructuredReference=Du Wei, Zhao Yichun, Li Boqun, et al. PPt: Backdoor attacks on pre-trained models via poisoned prompt tuning[C]//Proc of the 31st Int Joint Conf on Artificial Intelligence (IJCAI−22). San Francisco, CA: Morgan Kaufmann: 2022: 680−686, articleTitle=null, refAbstract=null), Reference(id=1327018620313513987, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=61, rfOrder=62, authorNames=null, journalName=null, refType=null, unstructuredReference=Chung H W, Hou Le, Longpre S, et al. Scaling instruction-finetuned language models[J]. Journal of Machine Learning Research, 2024, 25(70): 1−53, articleTitle=null, refAbstract=null), Reference(id=1327018620393205764, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=62, rfOrder=63, 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 20th 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=1327018620464508933, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=63, rfOrder=64, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Yufei, Shen Chao, Wang Cong, et al. Teacher model fingerprinting attacks against transfer learning[C]//Proc of the 31st USENIX Security Symp (USENIX Security 22). Berkeley, CA: USENIX Association, 2022: 3593−3610, articleTitle=null, refAbstract=null), Reference(id=1327018620531617798, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=64, rfOrder=65, authorNames=null, journalName=null, refType=null, unstructuredReference=Tian Yulong, Suya F, Suri A, et al. Manipulating transfer learning for property inference[C]//Proc of the 36th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 15975−15984, articleTitle=null, refAbstract=null), Reference(id=1327018620602920967, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=65, rfOrder=66, authorNames=null, journalName=null, refType=null, unstructuredReference=Song Congzheng, Raghunathan A. Information leakage in embedding models[C]//Proc of the 27th ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2020: 377−390, articleTitle=null, refAbstract=null), Reference(id=1327018620695195656, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=66, rfOrder=67, authorNames=null, journalName=null, refType=null, unstructuredReference=Carlini N, Tramer F, Wallace E, et al. Extracting training data from large language models[C]//Proc of the 30th USENIX Security Symp (USENIX Security 21). Berkeley, CA: USENIX Association, 2021: 2633−2650, articleTitle=null, refAbstract=null), Reference(id=1327018620753915913, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=67, rfOrder=68, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Hongbin, Jia Jinyuan, Qu Wenjie, et al. EncoderMI: Membership inference against pre-trained encoders in contrastive learning[C]//Proc of the 28th ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2021: 2081−2095, articleTitle=null, refAbstract=null), Reference(id=1327018620825219082, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=68, rfOrder=69, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Yupei, Jia Jinyuan, Liu Hongbin, et al. StolenEncoder: Stealing pre-trained encoders in self-supervised learning[C]//Proc of the 29th ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2022: 2115−2128, articleTitle=null, refAbstract=null), Reference(id=1327018620888133643, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=69, rfOrder=70, authorNames=null, journalName=null, refType=null, unstructuredReference=Sha Zeyang, He Xinlei, Yu Ning, et al. Can’t steal? Cont-steal! Contrastive stealing attacks against image encoders[C]//Proc of the 40th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 16373−16383, articleTitle=null, refAbstract=null), Reference(id=1327018620959436812, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=70, rfOrder=71, authorNames=null, journalName=null, refType=null, unstructuredReference=Hong S, Panaitescu-Liess M A, Kaya Y, et al. Qu-anti-zation: Exploiting quantization artifacts for achieving adversarial outcomes[J]. Advances in Neural Information Processing Systems, 2021, 34(1): 9303−9316, articleTitle=null, refAbstract=null), Reference(id=1327018621022351373, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=71, rfOrder=72, authorNames=null, journalName=null, refType=null, unstructuredReference=Ma Hua, Qiu Huming, Gao Yansong, et al. Quantization backdoors to deep learning commercial frameworks[J]. IEEE Transactions on Dependable and Secure Computing, 2023, 21(3): 1155−1172, articleTitle=null, refAbstract=null), Reference(id=1327018621089460238, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=72, rfOrder=73, authorNames=null, journalName=null, refType=null, unstructuredReference=Tian Yulong, Suya F, Xu Fengyan, et al. Stealthy backdoors as compression artifacts[J]. IEEE Transactions on Information Forensics and Security, 2022, 17: 1372−1387, articleTitle=null, refAbstract=null), Reference(id=1327018621169152015, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=73, rfOrder=74, authorNames=null, journalName=null, refType=null, unstructuredReference=Phan H, Shi Cong, Xie Yi, et al. RIBAC: Towards robust and imperceptible backdoor attack against compact DNN[C]//Proc of the 17th European Conf on Computer Vision 2022. Berlin: Springer, 2022: 708−724, articleTitle=null, refAbstract=null), Reference(id=1327018621236260880, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=74, rfOrder=75, authorNames=null, journalName=null, refType=null, unstructuredReference=Ge Yunjie, Wang Qian, Zheng Baolin, et al. Anti-distillation backdoor attacks: Backdoors can really survive in knowledge distillation[C]//Proc of the 29th ACM Int Conf on Multimedia. New York: ACM, 2021: 826−834, articleTitle=null, refAbstract=null), Reference(id=1327018621290786833, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=75, rfOrder=76, authorNames=null, journalName=null, refType=null, unstructuredReference=Qi Xiangyu, Xie Tinghao, Pan Ruizhe, et al. Towards practical deployment-stage backdoor attack on deep neural networks[C]//Proc of the 39th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 13347−13357, articleTitle=null, refAbstract=null), Reference(id=1327018621353701394, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=76, rfOrder=77, authorNames=null, journalName=null, refType=null, unstructuredReference=Zou A, Wang Zifan, Kolter J Z, et al. Universal and transferable adversarial attacks on aligned language models[J]. arXiv preprint, arXiv: 2307.15043, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018621416615955, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=77, rfOrder=78, authorNames=null, journalName=null, refType=null, unstructuredReference=Wei A, Haghtalab N, Steinhardt J. Jailbroken: How does llm safety training fail?[J]. Advances in Neural Information Processing Systems, 2024, 36(1): 80079-80110, articleTitle=null, refAbstract=null), Reference(id=1327018621492113428, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Wei A,Haghtalab N,Steinhardt J. Jailbroken:How does llm safety training fail?[J]. Advances in Neural Information Processing Systems,2024,36(1):80079-80110, articleTitle=null, refAbstract=null), Reference(id=1327018621563416597, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Shen Xinyue, Chen Zeyuan, Backes M, et al. " do anything now": Characterizing and evaluating in-the-wild jailbreak prompts on large language models[C]//Proc of the 31st on ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2024: 1671−1685, articleTitle=null, refAbstract=null), Reference(id=1327018625132769302, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Zanella-Béguelin S, Wutschitz L, Tople S, et al. Analyzing information leakage of updates to natural language models[C]//Proc of the 27th ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2020: 363−375, articleTitle=null, refAbstract=null), Reference(id=1327018625241821207, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Panchendrarajan R, Bhoi S. Dataset reconstruction attack against language models[C/OL]//Proc of the 30th Int Joint Conf on Artificial Intelligence. 2021[2021-07-01]. http://cdap.sliit.lk/bitstream/123456789/2045/1/DatasetReconstructionAttackagainstLanguageModels.pdf, articleTitle=null, refAbstract=null), Reference(id=1327018625334095896, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Lukas N, Salem A, Sim R, et al. Analyzing leakage of personally identifiable information in language models[C]//Proc of the 44th IEEE Symp on Security and Privacy (SP). Piscataway, NJ: IEEE, 2023: 346−363, articleTitle=null, refAbstract=null), Reference(id=1327018625434759193, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Keskar N S, McCann B, Xiong Caiming, et al. The thieves on sesame street are polyglots-extracting multilingual models from monolingual APIs[C]//Proc of the 25th Conf on Empirical Methods in Natural Language Processing (EMNLP). Stroudsburg, PA: ACL, 2020: 6203−6207, articleTitle=null, refAbstract=null), Reference(id=1327018625514450970, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Xu Qiongkai, He Xuanli, Lyu Lingjuan, et al. Student surpasses teacher: Imitation attack for black-box NLP APIs[C]//Proc of the 29th Int Conf on Computational Linguistics. Stroudsburg, PA: ACL, 2022: 2849−2860, articleTitle=null, refAbstract=null), Reference(id=1327018625581559835, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Li Zongjie, Wang Chaozheng, Ma Pingchuan, et al. On extracting specialized code abilities from large language models: A feasibility study[C]//Proc of the 46th IEEE/ACM Int Conf on Software Engineering. 2024: 1−13, articleTitle=null, refAbstract=null), Reference(id=1327018625644474396, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Feng Shiwei, Tao Guanhong, Cheng Siyuan, et al. Detecting backdoors in pre-trained encoders[C]//Proc of the 40th IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2023: 16352−16362, articleTitle=null, refAbstract=null), Reference(id=1327018625745137693, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Zhu Biru, Qin Yujia, Cui Ganqu, et al. Moderate-fitting as a natural backdoor defender for pre-trained language models[J]. Advances in Neural Information Processing Systems, 2022, 35(1): 1086−1099, articleTitle=null, refAbstract=null), Reference(id=1327018625799663646, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Zhang Xiaoyu, Jin Yulin, Wang Tao, et al. Purifier: Plug-and-play backdoor mitigation for pre-trained models via anomaly activation suppression[C]//Proc of the 30th ACM Int Conf on Multimedia. New York: ACM, 2022: 4291−4299, articleTitle=null, refAbstract=null), Reference(id=1327018625862578207, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, 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=Shan S, Bhagoji A N, Zheng Haitao, et al. Poison forensics: Traceback of data poisoning attacks in neural networks[C]//Proc of the 31st USENIX Security Symp (USENIX Security 22). Berkeley, CA: USENIX Association, 2022: 3575−3592, articleTitle=null, refAbstract=null), Reference(id=1327018625925492768, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=89, rfOrder=91, authorNames=null, journalName=null, refType=null, unstructuredReference=Cheng Siyuan, Tao Guanhong, Liu Yingqi, et al. BEAGLE: Forensics of deep learning backdoor attack for better defense[J]. arXiv preprint, arXiv: 2301.06241, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018625984213025, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=90, rfOrder=92, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Kang, Dolan-Gavitt B, Garg S. Fine-pruning: Defending against backdooring attacks on deep neural networks[C]//Proc of the 21st Int Symp on Research in Attacks, Intrusions, and Defenses. Berlin: Springer, 2018: 273−294, articleTitle=null, refAbstract=null), Reference(id=1327018626034544674, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=91, rfOrder=93, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Yige, Lyu Xixiang, Koren N, et al. Neural attention distillation: Erasing backdoor triggers from deep neural networks[J]. arXiv preprint, arXiv: 2101.05930, 2021, articleTitle=null, refAbstract=null), Reference(id=1327018626097459235, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=92, rfOrder=94, authorNames=null, journalName=null, refType=null, unstructuredReference=Papernot N, McDaniel P, Wu Xi, et al. Distillation as a defense to adversarial perturbations against deep neural networks[C]//Proc of the 37th IEEE Symp on Security and Privacy (SP). Piscataway, NJ: IEEE, 2016: 582−597, articleTitle=null, refAbstract=null), Reference(id=1327018626156179492, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=93, rfOrder=95, authorNames=null, journalName=null, refType=null, unstructuredReference=Khalid F, Ali H, Tariq H, et al. Qusecnets: Quantization-based defense mechanism for securing deep neural network against adversarial attacks[C]//Proc of the 25th IEEE Int Symp on On-Line Testing and Robust System Design (IOLTS). Piscataway, NJ: IEEE, 2019: 182−187, articleTitle=null, refAbstract=null), Reference(id=1327018626214899749, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=94, rfOrder=96, authorNames=null, journalName=null, refType=null, unstructuredReference=Dong Xinshuai, Luu A T, Lin Min, et al. How should pre-trained language models be fine-tuned towards adversarial robustness?[J]. Advances in Neural Information Processing Systems, 2021, 34(1): 4356−4369, articleTitle=null, refAbstract=null), Reference(id=1327018626282008614, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=95, rfOrder=97, authorNames=null, journalName=null, refType=null, unstructuredReference=Jiang Lan, Zhou Hao, Lin Yankai, et al. ROSE: Robust selective fine-tuning for pre-trained language models[C]//Proc of the 27th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA, ACL: 2022: 2886−2897, articleTitle=null, refAbstract=null), Reference(id=1327018626336534567, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=96, rfOrder=98, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Hongbin, Reiter M K, Gong N Z. Mudjacking: Patching backdoor vulnerabilities in foundation models[J]. arXiv preprint, arXiv: 2402.14977, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018626399449128, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=97, rfOrder=99, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Zhiyuan, Lyu Lingjuan, Ma Xingjun, et al. Fine-mixing: Mitigating backdoors in fine-tuned language models[C]/Proc of the 27th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA, ACL: 2022: 355−372, articleTitle=null, refAbstract=null), Reference(id=1327018626462363689, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=98, rfOrder=100, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Zhiyuan, Chen Deli, Zhou Hao, et al. Diffusion theory as a scalpel: Detecting and purifying poisonous dimensions in pre-trained language models caused by backdoor or bias[C]//Proc of the 61st Association for Computational Linguistics. Stroudsburg, PA: ACL, 2023: 2495−2517, articleTitle=null, refAbstract=null), Reference(id=1327018626529472554, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=99, rfOrder=101, authorNames=null, journalName=null, refType=null, unstructuredReference=Sheng Lijun, Liang Jian, He Ran, et al. AdaptGuard: Defending against universal attacks for model adaptation[C]//Proc of the 39th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 19093−19103, articleTitle=null, refAbstract=null), Reference(id=1327018626596581419, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=100, rfOrder=102, authorNames=null, journalName=null, refType=null, unstructuredReference=Sheng Lijun, Liang Jian, He Ran, et al. Can we trust the unlabeled target data? Towards backdoor attack and defense on model adaptation[J]. arXiv preprint, arXiv: 2401.06030, 2024, articleTitle=null, refAbstract=null), Reference(id=1327018626693050412, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=101, rfOrder=103, authorNames=null, journalName=null, refType=null, unstructuredReference=Ahmed S, Al Arafat A, Rizve M N, et al. SSDA: Secure source-free domain adaptation[C]//Proc of the 39th IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2023: 19180−19190, articleTitle=null, refAbstract=null), Reference(id=1327018626764353581, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=102, rfOrder=104, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Ziqi, Li Yuanchun, Wang Jindong, et al. ReMoS: Reducing defect inheritance in transfer learning via relevant model slicing[C]//Proc of the 44th Int Conf on Software Engineering. Piscataway, NJ: IEEE, 2022: 1856−1868, articleTitle=null, refAbstract=null), Reference(id=1327018626823073838, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=103, rfOrder=105, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Jie, Wang Leye, Han Xiao. Safety and performance, why not both? bi-objective optimized model compression against heterogeneous attacks toward AI software deployment[J]. IEEE Transactions on Software Engineering, 2024, 50(3): 376−390, articleTitle=null, refAbstract=null), Reference(id=1327018626894377007, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=104, rfOrder=106, authorNames=null, journalName=null, refType=null, unstructuredReference=Tian Yongqiang, Zhang Wuqi, Wen Ming, et al. Finding deviated behaviors of the compressed DNN models for image classifications[J]. ACM Transactions on Software Engineering and Methodology, 2023, 32(5): 1−32, articleTitle=null, refAbstract=null), Reference(id=1327018626948902960, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=105, rfOrder=107, authorNames=null, journalName=null, refType=null, unstructuredReference=Xiao Dongwei, Liu Zhibo, Yuan Yuanyuan, et al. Metamorphic testing of deep learning compilers[J]. ACM on Measurement and Analysis of Computing Systems, 2022, 6(1): 1−28, articleTitle=null, refAbstract=null), Reference(id=1327018627007623217, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=106, rfOrder=108, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Jiawei, Lin Jinkun, Ruffy F, et al. NNSmith: Generating diverse and valid test cases for deep learning compilers[C]//Proc of the 28th ACM Int Conf on Architectural Support for Programming Languages and Operating Systems, Volume 2. New York: ACM, 2023: 530−543, articleTitle=null, refAbstract=null), Reference(id=1327018627078926386, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=107, rfOrder=109, authorNames=null, journalName=null, refType=null, unstructuredReference=Ma Haoyang, Shen Qingchao, Tian Yongqiang, et al. Fuzzing deep learning compilers with HirGen[C]//Proc of the 32nd ACM SIGSOFT Int Symp on Software Testing and Analysis. New York: ACM, 2023: 248−260, articleTitle=null, refAbstract=null), Reference(id=1327018627133452339, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=108, rfOrder=110, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Xin, Lu Jinzhu, Gui Tao, et al. TextFusion: Privacy-preserving pre-trained model inference via token fusion[C]//Proc of the 27th Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA, ACL: 2022: 8360−8371, articleTitle=null, refAbstract=null), Reference(id=1327018627200561204, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=109, rfOrder=111, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Xin, Lu Yi, Ma Ruotian, et al. TextObfuscator: Making pre-trained language model a privacy protector via obfuscating word representations[C]//Proc of the 61st Association for Computational Linguistics. Stroudsburg, PA: ACL, 2023: 5459−5473, articleTitle=null, refAbstract=null), Reference(id=1327018627259281461, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=110, rfOrder=112, authorNames=null, journalName=null, refType=null, unstructuredReference=Modelscope. ModelScope: Bring the notion of model-as-a-service to life[EB/OL]. (2022-11-03)[2024-05-01]. https://github.com/modelscope/modelscope, articleTitle=null, refAbstract=null), Reference(id=1327018627330584630, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=111, rfOrder=113, authorNames=null, journalName=null, refType=null, unstructuredReference=PaddlePaddle. PaddleHub―An open-source deep learning platform originated from industrial practice[EB/OL]. (2019-07-08)[2023-03-15]. https://www.paddlepaddle.org.cn/hub, articleTitle=null, refAbstract=null), Reference(id=1327018627393499191, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=112, rfOrder=114, authorNames=null, journalName=null, refType=null, unstructuredReference=Pytorch. PyTorch Hub. [EB/OL]. (2019-06-01)[2023-05-01]. https://pytorch.org/hub/, articleTitle=null, refAbstract=null), Reference(id=1327018630941880376, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=113, rfOrder=115, authorNames=null, journalName=null, refType=null, unstructuredReference=ONNX. ONNX Model Zoo[EB/OL]. (2017-04-20)[2023-06-01]. https://github.com/onnx/models, articleTitle=null, refAbstract=null), Reference(id=1327018631067709497, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=114, rfOrder=116, authorNames=null, journalName=null, refType=null, unstructuredReference=Debenedetti E, Severi G, Carlini N, et al. Privacy side channels in machine learning systems[C]//Proc of the 33rd USENIX Security Symp (USENIX Security 24). Berkeley, CA: USENIX Association, 2024: 6861−6848, articleTitle=null, refAbstract=null), Reference(id=1327018631193538618, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=115, rfOrder=117, authorNames=null, journalName=null, refType=null, unstructuredReference=Tan Qi, Li Qi, Zhao Yi, et al. Defending against data reconstruction attacks in federated learning: An information theory approach[J]. arXiv preprint, arXiv: 2403.01268, 2024, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1327018603062342523, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, xref=1, ext=[AuthorCompanyExt(id=1327018603074925436, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603062342523, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1College of Information Engineering, Zhejiang University of Technology University, Hangzhou 310023), AuthorCompanyExt(id=1327018603087508349, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603062342523, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1浙江工业大学信息工程学院 杭州 310023)]), AuthorCompany(id=1327018603200754558, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, xref=2, ext=[AuthorCompanyExt(id=1327018603209143167, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603200754558, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Institute of Cyberspace Security, Zhejiang University of Technology University, Hangzhou 310023), AuthorCompanyExt(id=1327018603217531776, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603200754558, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2浙江工业大学网络空间安全研究院 杭州 310023)]), AuthorCompany(id=1327018603293029249, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, xref=3, ext=[AuthorCompanyExt(id=1327018603305612162, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603293029249, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3College of Computer Science and Technology, Zhejiang University, Hangzhou 310007), AuthorCompanyExt(id=1327018603309806467, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603293029249, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
3浙江大学计算机科学与技术学院 杭州 310007)]), AuthorCompany(id=1327018603381109636, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, xref=4, ext=[AuthorCompanyExt(id=1327018603389498245, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603381109636, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4College of Computer Science and Technology, Zhejiang University of Technology University, Hangzhou 310023), AuthorCompanyExt(id=1327018603397886854, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, companyId=1327018603381109636, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
4浙江工业大学计算机科学与技术学院 杭州 310023)])], figs=[ArticleFig(id=1327018607395058611, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=EN, label=Figure 1, caption=
Supply chain of deep learning model, figureFileSmall=jITDoRYnV/uconJz++mOaw==, figureFileBig=jK6VLcM1ZQ7DxysH3+9X7w==, tableContent=null), ArticleFig(id=1327018607466361780, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=CN, label=图1, caption=
深度学习模型供应链, figureFileSmall=jITDoRYnV/uconJz++mOaw==, figureFileBig=jK6VLcM1ZQ7DxysH3+9X7w==, tableContent=null), ArticleFig(id=1327018607638328246, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=EN, label=Figure 2, caption=
An example of real supply chain in Hugging Face, figureFileSmall=65+6EHwG6poqDarYYijSBA==, figureFileBig=EoPPYyipVunu1PNVeHcN1A==, tableContent=null), ArticleFig(id=1327018607709631415, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=CN, label=图2, caption=
Hugging Face上真实的供应链举例, figureFileSmall=65+6EHwG6poqDarYYijSBA==, figureFileBig=EoPPYyipVunu1PNVeHcN1A==, tableContent=null), ArticleFig(id=1327018611316732856, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=EN, label=Figure 3, caption=
Potential risks in each stage of supply chain, figureFileSmall=O/65iBWtQ6sP4viEZ47EBA==, figureFileBig=5g6wyH3QOQKCG/pvxl/+Ag==, tableContent=null), ArticleFig(id=1327018611400618937, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=CN, label=图3, caption=
供应链中各阶段的潜在威胁, figureFileSmall=O/65iBWtQ6sP4viEZ47EBA==, figureFileBig=5g6wyH3QOQKCG/pvxl/+Ag==, tableContent=null), ArticleFig(id=1327018611484505018, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=EN, label=Figure 4, caption=
Attacks and defense methods in DNN supply chain, figureFileSmall=xOZ40txec+WC1+YiDQJmBw==, figureFileBig=kGcaUIayfF6ek/DYJiEdRA==, tableContent=null), ArticleFig(id=1327018611564196795, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=CN, label=图4, caption=
深度神经网络供应链中的攻击和防御方法, figureFileSmall=xOZ40txec+WC1+YiDQJmBw==, figureFileBig=kGcaUIayfF6ek/DYJiEdRA==, tableContent=null), ArticleFig(id=1327018611622917052, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=EN, label=Table 1, caption=
Summary of Attacks in the Designing Stage of Models, figureFileSmall=null, figureFileBig=null, tableContent=
攻击 类型 | 方法 | 攻击手段 | 是否中毒 数据 | 攻击者知识 | 领域 | 目标模型 | 攻击结果 |
|---|
| 上游数据集 | 下游任务 | 下游数据集 |
|---|
| 注:攻击者知识中,○表示未知,◐表示已知或部分已知,●表示全知.ASR表示攻击成功率. |
下游任务 相关 | RIPPLe[34] | 修改已有权重 | 是 | ○ | ○ | ● | NLP | BERT | SST-2上ASR=0.18 |
| LWP[35] | 修改已有权重 | 是 | ◐ | ○ | ◐ | NLP | BERT | SST-2上ASR=0.57 |
| TrojanLM[36] | 修改已有权重 | 是 | ○ | ○ | ◐ | NLP | BERT, GPT-2, XLNet | SQuAD 1.1上ASR=0.83 |
| BadPrompt[37] | 修改已有权重 | 是 | ○ | ○ | ◐ | NLP | 上游RoBERTa-large 下游P-tuning, DART | SST-2上ASR=1 |
| BadEncoder[39] | 从头训练模型/ 修改已有权重 | 是 | ○ | ● | ◐ | CV | 上游 ResNet18 on SimCLR 下游全连接网络 | 上游CIFAR-10, 下游STL-10 ASR=0.8 |
| PoisonedEncoder[40] | 中毒预训练 数据 | 是 | ○ | ● | ◐ | CV | 上游ResNet18 on SimCLR 下游单层全连接 | 上游CIFAR-10, 下游STL-10 ASR=0.8 |
| CorruptEncoder[42] | 从头训练模型 | 是 | ◐ | ● | ◐ | CV | 上游ResNet18 on MoCo-v2 下游线性分类器 | 下游ImageNet100 ASR=0.96 |
下游任务 无关 | Ji等人[43] | 从头训练模型 | 是 | ◐ | ○ | ○ | CV,语音 | Inception.v3, Pannous, VGG16 | 上游ImageNet, 下游ISIC ASR=0.98 |
| BadPre[44] | 从头训练模型 | 是 | ◐ | ○ | ○ | NLP | BERT | SST-2上ASR=0.51 |
| NeuBA[45] | 从头训练模型 | 是 | ◐ | ○ | ○ | NLP,CV | BERT, RoBERTa, ViT | SST-2上ASR=1 |
| Shen等人[29] | 从头训练模型 | 是 | ◐ | ○ | ○ | NLP | BERT, XLNet, BART, RoBERTa, DeBERTa, ALBERT | SST-2上ASR=1 |
| Lv等人[46] | 修改已有权重 | 是 | ○ | ○ | ○ | CV | ViT, CNN, GPT-2, TabNet, AutoEncoder | ImageNet上ASR=1 |
| NOTABLE[47] | 修改已有权重 | 否 | ○ | ○ | ○ | NLP | BERT, Distil-BERT | SST-2上ASR=1 |
| UOR[48] | 从头训练模型 | 是 | ○ | ○ | ○ | NLP | BERT, RoBERTa, DeBERTa | SST-2上ASR=0.91 |
| TransTroj[49] | 从头训练模型 | 是 | ◐ | ○ | ○ | CV | ResNet, VGG, ViT, CLIP | 上游ImageNet, 下游CIFAR-10 ASR=0.99 |
| TFLexAttack[50] | 修改模型组件 | 否 | ○ | ○ | ○ | NLP | BERT, RoBERTa, XLNet, GPT2, ALBERT | SST-2上ASR=0.875 |
| Li等人[52] | 从头训练模型 | 是 | ◐ | ○ | ○ | 代码 | PLBART, CodeT5 | CodeXGLUE上ASR=0.97 |
), ArticleFig(id=1327018611706803133, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=CN, label=表1, caption=
模型设计阶段的攻击总结
, figureFileSmall=null, figureFileBig=null, tableContent=
攻击 类型 | 方法 | 攻击手段 | 是否中毒 数据 | 攻击者知识 | 领域 | 目标模型 | 攻击结果 |
|---|
| 上游数据集 | 下游任务 | 下游数据集 |
|---|
| 注:攻击者知识中,○表示未知,◐表示已知或部分已知,●表示全知.ASR表示攻击成功率. |
下游任务 相关 | RIPPLe[34] | 修改已有权重 | 是 | ○ | ○ | ● | NLP | BERT | SST-2上ASR=0.18 |
| LWP[35] | 修改已有权重 | 是 | ◐ | ○ | ◐ | NLP | BERT | SST-2上ASR=0.57 |
| TrojanLM[36] | 修改已有权重 | 是 | ○ | ○ | ◐ | NLP | BERT, GPT-2, XLNet | SQuAD 1.1上ASR=0.83 |
| BadPrompt[37] | 修改已有权重 | 是 | ○ | ○ | ◐ | NLP | 上游RoBERTa-large 下游P-tuning, DART | SST-2上ASR=1 |
| BadEncoder[39] | 从头训练模型/ 修改已有权重 | 是 | ○ | ● | ◐ | CV | 上游 ResNet18 on SimCLR 下游全连接网络 | 上游CIFAR-10, 下游STL-10 ASR=0.8 |
| PoisonedEncoder[40] | 中毒预训练 数据 | 是 | ○ | ● | ◐ | CV | 上游ResNet18 on SimCLR 下游单层全连接 | 上游CIFAR-10, 下游STL-10 ASR=0.8 |
| CorruptEncoder[42] | 从头训练模型 | 是 | ◐ | ● | ◐ | CV | 上游ResNet18 on MoCo-v2 下游线性分类器 | 下游ImageNet100 ASR=0.96 |
下游任务 无关 | Ji等人[43] | 从头训练模型 | 是 | ◐ | ○ | ○ | CV,语音 | Inception.v3, Pannous, VGG16 | 上游ImageNet, 下游ISIC ASR=0.98 |
| BadPre[44] | 从头训练模型 | 是 | ◐ | ○ | ○ | NLP | BERT | SST-2上ASR=0.51 |
| NeuBA[45] | 从头训练模型 | 是 | ◐ | ○ | ○ | NLP,CV | BERT, RoBERTa, ViT | SST-2上ASR=1 |
| Shen等人[29] | 从头训练模型 | 是 | ◐ | ○ | ○ | NLP | BERT, XLNet, BART, RoBERTa, DeBERTa, ALBERT | SST-2上ASR=1 |
| Lv等人[46] | 修改已有权重 | 是 | ○ | ○ | ○ | CV | ViT, CNN, GPT-2, TabNet, AutoEncoder | ImageNet上ASR=1 |
| NOTABLE[47] | 修改已有权重 | 否 | ○ | ○ | ○ | NLP | BERT, Distil-BERT | SST-2上ASR=1 |
| UOR[48] | 从头训练模型 | 是 | ○ | ○ | ○ | NLP | BERT, RoBERTa, DeBERTa | SST-2上ASR=0.91 |
| TransTroj[49] | 从头训练模型 | 是 | ◐ | ○ | ○ | CV | ResNet, VGG, ViT, CLIP | 上游ImageNet, 下游CIFAR-10 ASR=0.99 |
| TFLexAttack[50] | 修改模型组件 | 否 | ○ | ○ | ○ | NLP | BERT, RoBERTa, XLNet, GPT2, ALBERT | SST-2上ASR=0.875 |
| Li等人[52] | 从头训练模型 | 是 | ◐ | ○ | ○ | 代码 | PLBART, CodeT5 | CodeXGLUE上ASR=0.97 |
), ArticleFig(id=1327018611799077823, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=EN, label=Table 2, caption=
Summary of Attacks in the Stage of Secondary Development of the Model, figureFileSmall=null, figureFileBig=null, tableContent=
针对 操作 | 方法 | 攻击类型 | 威胁CIA | 目标操作 | 攻击者知识 | 领域 | 攻击结果 |
|---|
上游 数据集 | 下游 模型 |
|---|
| 注:攻击者知识中,○表示未知,◐表示已知或部分已知,●表示全知.ASR表示攻击成功率,“/”表示该场景并无设置. |
| 迁移 | Wang等人[53] | 对抗攻击 | 推理数据完整性 | 特征提取、全模型微调 | ○ | ○ | CV | 上游ImageNet, 下游GTSRB ASR=0.96 |
| Latent backdoor[54] | 后门攻击 | 训练数据完整性 | 模型部分微调 | ● | ○ | CV | 上游GTSRB, 下游LISA ASR=1 |
| Wang等人[55] | 后门攻击 | 训练过程完整性 | 模型部分微调 | ○ | ○/● | CV、信号 | 上游VGG-FACE, 下游LFW ASR=0.97 |
Incremental backdoor[57] | 后门攻击 | 训练数据完整性 | 类别增量学习 | ● | / | CV | CIFAR-10 ASR=1 |
| L4A[58] | 对抗攻击 | 推理数据完整性 | 自监督学习的下游迁移 | ◐ | / | CV | 上游ILSVRC2012, 下游SVHN ASR=0.95 |
| PPT[60] | 后门攻击 | 训练数据完整性 | 提示微调 | ● | / | NLP | SST-2上ASR=0.91 |
| Xu等人[62] | 后门攻击 | 训练过程完整性 | 指令微调 | ◐ | / | NLP | SST-2上ASR=0.99 |
| Chen等人[63] | 模型逆向攻击 | 模型机密性 | 特征提取 | ○ | ○ | CV | MNIST上ASR=1 |
| Tian等人[64] | 属性推理攻击 | 数据机密性 | 模型部分微调 | ● | ○/● | CV | 上游VGGFace, 下游MAADFace AUC=1 |
| Song等人[65] | 嵌入逆向攻击、属性 推理攻击、成员推理攻击 | 数据机密性、 模型机密性 | / | ○ | / | NLP | Wikipedia上F1=0.6 |
| Carlini等人[66] | 训练数据逆向攻击 | 数据机密性 | / | ○ | / | NLP | TPR=33.5% |
| EncoderMI[67] | 成员推理攻击 | 数据机密性 | / | ○ | / | CV | CIFAR-10 Recall=0.73 |
| StolenEncoder[68] | 模型窃取攻击 | 模型机密性 | / | ○ | ○/● | CV | 上游CIFAR-10, 下游SVHN acc=0.77 |
| Cont-Steal[69] | 模型窃取攻击 | 模型机密性 | / | ○ | ● | CV | 上游CIFAR-10, 下游SVHN acc=0.52 |
| 压缩 | Hong等人[70] | 后门攻击 | 训练过程完整性 | 训练中量化 | ○ | ● | CV | CIFAR-10 8bits ASR=0.81 |
| PQ backdoor[71] | 后门攻击 | 训练数据完整性 | 训练后量化 | ● | ○ | CV | MNIST VGG16 ASR=0.99 |
| Tian等人[72] | 后门攻击 | 训练数据完整性、 训练数据完整性 | 量化感知训练、 自动压缩 | ● | / | CV | CIFAR-10 VGG-16 ASR=0.89 |
| RIBAC[73] | 后门攻击 | 训练数据完整性 | 权重剪枝 | ● | / | CV | CIFAR-10 ResNet-18 32X ASR=1 |
| ADBA[74] | 后门攻击 | 训练数据完整性 | 基于置信度的知识蒸馏 | ● | ○ | CV | GTSRB ASR=0.94 |
), ArticleFig(id=1327018611908129728, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=CN, label=表2, caption=
模型二次开发阶段的攻击总结
, figureFileSmall=null, figureFileBig=null, tableContent=
针对 操作 | 方法 | 攻击类型 | 威胁CIA | 目标操作 | 攻击者知识 | 领域 | 攻击结果 |
|---|
上游 数据集 | 下游 模型 |
|---|
| 注:攻击者知识中,○表示未知,◐表示已知或部分已知,●表示全知.ASR表示攻击成功率,“/”表示该场景并无设置. |
| 迁移 | Wang等人[53] | 对抗攻击 | 推理数据完整性 | 特征提取、全模型微调 | ○ | ○ | CV | 上游ImageNet, 下游GTSRB ASR=0.96 |
| Latent backdoor[54] | 后门攻击 | 训练数据完整性 | 模型部分微调 | ● | ○ | CV | 上游GTSRB, 下游LISA ASR=1 |
| Wang等人[55] | 后门攻击 | 训练过程完整性 | 模型部分微调 | ○ | ○/● | CV、信号 | 上游VGG-FACE, 下游LFW ASR=0.97 |
Incremental backdoor[57] | 后门攻击 | 训练数据完整性 | 类别增量学习 | ● | / | CV | CIFAR-10 ASR=1 |
| L4A[58] | 对抗攻击 | 推理数据完整性 | 自监督学习的下游迁移 | ◐ | / | CV | 上游ILSVRC2012, 下游SVHN ASR=0.95 |
| PPT[60] | 后门攻击 | 训练数据完整性 | 提示微调 | ● | / | NLP | SST-2上ASR=0.91 |
| Xu等人[62] | 后门攻击 | 训练过程完整性 | 指令微调 | ◐ | / | NLP | SST-2上ASR=0.99 |
| Chen等人[63] | 模型逆向攻击 | 模型机密性 | 特征提取 | ○ | ○ | CV | MNIST上ASR=1 |
| Tian等人[64] | 属性推理攻击 | 数据机密性 | 模型部分微调 | ● | ○/● | CV | 上游VGGFace, 下游MAADFace AUC=1 |
| Song等人[65] | 嵌入逆向攻击、属性 推理攻击、成员推理攻击 | 数据机密性、 模型机密性 | / | ○ | / | NLP | Wikipedia上F1=0.6 |
| Carlini等人[66] | 训练数据逆向攻击 | 数据机密性 | / | ○ | / | NLP | TPR=33.5% |
| EncoderMI[67] | 成员推理攻击 | 数据机密性 | / | ○ | / | CV | CIFAR-10 Recall=0.73 |
| StolenEncoder[68] | 模型窃取攻击 | 模型机密性 | / | ○ | ○/● | CV | 上游CIFAR-10, 下游SVHN acc=0.77 |
| Cont-Steal[69] | 模型窃取攻击 | 模型机密性 | / | ○ | ● | CV | 上游CIFAR-10, 下游SVHN acc=0.52 |
| 压缩 | Hong等人[70] | 后门攻击 | 训练过程完整性 | 训练中量化 | ○ | ● | CV | CIFAR-10 8bits ASR=0.81 |
| PQ backdoor[71] | 后门攻击 | 训练数据完整性 | 训练后量化 | ● | ○ | CV | MNIST VGG16 ASR=0.99 |
| Tian等人[72] | 后门攻击 | 训练数据完整性、 训练数据完整性 | 量化感知训练、 自动压缩 | ● | / | CV | CIFAR-10 VGG-16 ASR=0.89 |
| RIBAC[73] | 后门攻击 | 训练数据完整性 | 权重剪枝 | ● | / | CV | CIFAR-10 ResNet-18 32X ASR=1 |
| ADBA[74] | 后门攻击 | 训练数据完整性 | 基于置信度的知识蒸馏 | ● | ○ | CV | GTSRB ASR=0.94 |
), ArticleFig(id=1327018611983627201, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=EN, label=Table 3, caption=
Summary of Security Defense Methods in Model Supply Chain, figureFileSmall=null, figureFileBig=null, tableContent=
针对 阶段 | 方法 | 防护类型 | 具体环节 | 攻击不 可知 | 需要重 训练 | 防御者知识 | 领域 | 防御结果 |
|---|
上游 数据集 | 下游 模型 | 下游 数据集 |
|---|
| 注:攻击者知识中,○表示未知,◐表示已知或部分已知,●表示全知.ASR表示攻击成功率,“/”表示论文中未设置,acc表示精确率,#Logic Errors表示逻辑错误数,branch coverage表示分支覆盖率,recall表示召回率,#Bug表示错误数目. |
模型设 计阶段 | DECREE[85] | 后门检测 | 自监督学习 | 是 | 否 | ○/● | ○ | ○ | CV | 上游CIFAR-10,下游SVHN ASR=0.1 |
Moderate- fitting[86] | 后门防御 | 监督学习 | 是 | 是 | ● | ○ | ○ | NLP | SST-2 ASR=0.15 |
| Purifier[87] | 后门防御 | 监督学习 | 是 | 是 | ○ | ○ | ◐ | NLP | CIFAR-10 ResNet-18 ASR=0 |
| Shan等人[88] | 后门溯源 | 监督学习 | 是 | 否 | ● | / | / | CV | CIFAR-10 BadNet trace recall=0.98 |
| BEAGLE[89] | 后门溯源 | 监督学习 | 否 | 否 | ◐ | / | / | CV | TrojAI trace acc=0.874 |
二次开 发阶段 | RIFT[94] | 对抗防御 | 微调 | 是 | 否 | ○ | ● | ● | NLP | IMDB BERT ASR=0.23 |
| ROSE[95] | 对抗防御 | 微调 | 是 | 否 | ○ | ● | ● | NLP | SST-2 GLUE=65.02 |
| Mudjacking[96] | 后门防御 | 微调 | 是 | 是 | ◐ | ○ | ○ | CV、NLP | SST-2 ASR=0.14 |
Fine- mixing[97] | 后门防御 | 微调 | 是 | 否 | ○ | ● | ◐ | NLP | BERT BadWord ASR=0.25 |
Fine- purifying[98] | 后门检测、 防御 | 微调 | 是 | 否 | ○ | ● | ◐ | NLP | 上游CIFAR-10,下游STL10 ASR=0.02 |
| AdaptGuard[99] | 后门防御 | 迁移学习 | 是 | 是 | ● | ● | ● | CV | Office ResNet-50 ASR=0.15 |
| MixAdapt[100] | 后门防御 | 迁移学习 | 是 | 是 | ○ | ● | ◐ | CV | Office ResNet-50 ASR=0.17 |
| SSDA[101] | 后门防御 | 迁移学习 | 是 | 是 | ○ | ● | ● | CV | Office-Home ResNet-50 ASR=0.02 |
| ReMoS[102] | 对抗防御、 后门防御 | 迁移学习 | 是 | 是 | ○ | ● | ● | CV、NLP | ResNet18 DIR=0.15 |
| Jajal等人[20] | 故障分析 | 模型转换 | 是 | / | / | / | / | / | / |
| SafeCompress[103] | 隐私窃取防御 | 压缩 | 否 | 否 | ○ | ● | ● | CV、NLP | CIFAR-100 task acc=0.70 |
| DFLARE[104] | 模型测试 | 压缩 | 是 | / | ● | ○ | ○ | CV | MNIST LeNet-1 8bit acc=1 |
部署 阶段 | MT-DComp[105] | 编译器测试 | 模型编译 | / | / | / | / | / | / | TVM #Logic Errors =435 |
| NNSmith[106] | 编译器测试 | 模型编译 | / | / | / | / | / | / | TVM branch coverage=18.6% |
| HirGen[107] | 编译器测试 | 模型编译 | / | / | / | / | / | / | TVM #Bug=21 |
使用 阶段 | TextFusion[108] | 隐私窃取防御 | 云端推理 | 是 | 是 | ● | / | / | NLP | SST-2 ASR=0 |
| TextObfuscator[109] | 隐私窃取防御 | 云端推理 | 是 | 是 | ● | / | / | NLP | CoNLL2003 ASR=0.01 |
), ArticleFig(id=1327018612067513282, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=CN, label=表3, caption=
模型供应链中的安全防护方法总结
, figureFileSmall=null, figureFileBig=null, tableContent=
针对 阶段 | 方法 | 防护类型 | 具体环节 | 攻击不 可知 | 需要重 训练 | 防御者知识 | 领域 | 防御结果 |
|---|
上游 数据集 | 下游 模型 | 下游 数据集 |
|---|
| 注:攻击者知识中,○表示未知,◐表示已知或部分已知,●表示全知.ASR表示攻击成功率,“/”表示论文中未设置,acc表示精确率,#Logic Errors表示逻辑错误数,branch coverage表示分支覆盖率,recall表示召回率,#Bug表示错误数目. |
模型设 计阶段 | DECREE[85] | 后门检测 | 自监督学习 | 是 | 否 | ○/● | ○ | ○ | CV | 上游CIFAR-10,下游SVHN ASR=0.1 |
Moderate- fitting[86] | 后门防御 | 监督学习 | 是 | 是 | ● | ○ | ○ | NLP | SST-2 ASR=0.15 |
| Purifier[87] | 后门防御 | 监督学习 | 是 | 是 | ○ | ○ | ◐ | NLP | CIFAR-10 ResNet-18 ASR=0 |
| Shan等人[88] | 后门溯源 | 监督学习 | 是 | 否 | ● | / | / | CV | CIFAR-10 BadNet trace recall=0.98 |
| BEAGLE[89] | 后门溯源 | 监督学习 | 否 | 否 | ◐ | / | / | CV | TrojAI trace acc=0.874 |
二次开 发阶段 | RIFT[94] | 对抗防御 | 微调 | 是 | 否 | ○ | ● | ● | NLP | IMDB BERT ASR=0.23 |
| ROSE[95] | 对抗防御 | 微调 | 是 | 否 | ○ | ● | ● | NLP | SST-2 GLUE=65.02 |
| Mudjacking[96] | 后门防御 | 微调 | 是 | 是 | ◐ | ○ | ○ | CV、NLP | SST-2 ASR=0.14 |
Fine- mixing[97] | 后门防御 | 微调 | 是 | 否 | ○ | ● | ◐ | NLP | BERT BadWord ASR=0.25 |
Fine- purifying[98] | 后门检测、 防御 | 微调 | 是 | 否 | ○ | ● | ◐ | NLP | 上游CIFAR-10,下游STL10 ASR=0.02 |
| AdaptGuard[99] | 后门防御 | 迁移学习 | 是 | 是 | ● | ● | ● | CV | Office ResNet-50 ASR=0.15 |
| MixAdapt[100] | 后门防御 | 迁移学习 | 是 | 是 | ○ | ● | ◐ | CV | Office ResNet-50 ASR=0.17 |
| SSDA[101] | 后门防御 | 迁移学习 | 是 | 是 | ○ | ● | ● | CV | Office-Home ResNet-50 ASR=0.02 |
| ReMoS[102] | 对抗防御、 后门防御 | 迁移学习 | 是 | 是 | ○ | ● | ● | CV、NLP | ResNet18 DIR=0.15 |
| Jajal等人[20] | 故障分析 | 模型转换 | 是 | / | / | / | / | / | / |
| SafeCompress[103] | 隐私窃取防御 | 压缩 | 否 | 否 | ○ | ● | ● | CV、NLP | CIFAR-100 task acc=0.70 |
| DFLARE[104] | 模型测试 | 压缩 | 是 | / | ● | ○ | ○ | CV | MNIST LeNet-1 8bit acc=1 |
部署 阶段 | MT-DComp[105] | 编译器测试 | 模型编译 | / | / | / | / | / | / | TVM #Logic Errors =435 |
| NNSmith[106] | 编译器测试 | 模型编译 | / | / | / | / | / | / | TVM branch coverage=18.6% |
| HirGen[107] | 编译器测试 | 模型编译 | / | / | / | / | / | / | TVM #Bug=21 |
使用 阶段 | TextFusion[108] | 隐私窃取防御 | 云端推理 | 是 | 是 | ● | / | / | NLP | SST-2 ASR=0 |
| TextObfuscator[109] | 隐私窃取防御 | 云端推理 | 是 | 是 | ● | / | / | NLP | CoNLL2003 ASR=0.01 |
), ArticleFig(id=1327018612163982275, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=EN, label=Table 4, caption=
Summary of Pre-training Model Warehouse, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型仓库名称 | 模型 数目 | 数据集数目 | 模型具体分类 | 支持任务数 | 贡献者属性 | 支持功能 | 支持计算框架库 |
|---|
| Hugging Face[1] | 252 014 | 46 170 | 多模态、CV、语音、表格、 强化学习 | 36 | 开放式 | API | TensorFlow,PyTorch,Keras,Caffe,JAX,ONNX,PaddlePaddle,Core ML,FLAIR |
| ModelScope[110] | 955 | 492 | CV、NLP、语音、多模态、 科学计算、语种、其他 | 70 | 开放式 | API,GitHub | TensorFlow,PyTorch,ONNX |
| PaddleHub[111] | 135 | 10 000 | CV、视频、NLP、文心大模型、智 能语音、科学计算、跨模态、强化 学习、量子计算、表格、图神经网 络、时序技术、生物计算、智能推荐 | 14 | 开放式 | API,GitHub | PaddlePaddle |
| TensorFlow Hub[15] | 1 364 | 87 | 图像、文本、语音、视频 | 47 | 封闭式 | API,GitHub | TensorFlow |
| Model Zoo[2] | 1 211 | 0 | CV、NLP、生成式模型、强音频、图、自监督学习、健康和生物医学 | 9 | 封闭式 | GitHub | TensorFlow,PyTorch,Keras,Caffe, JAX,MXNet,Chainer |
| PyTorch Hub[112] | 52 | 0 | 音频、生成式模型、NLP、可脚本化模型、CV | 未知 | 封闭式 | GitHub | PyTorch |
| ONNX Model Zoo[113] | 55 | 0 | CV、NLP、语音 | 10 | 封闭式 | GitHub | ONNX |
| NVIDIA NGC[16] | 560 | 34 | CV、NLP、语音、其他 | 14 | 商业化 | API | PyTorch,TensorFlow |
), ArticleFig(id=1327018612235285444, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018598960313188, language=CN, label=表4, caption=
预训练模型仓库总结
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型仓库名称 | 模型 数目 | 数据集数目 | 模型具体分类 | 支持任务数 | 贡献者属性 | 支持功能 | 支持计算框架库 |
|---|
| Hugging Face[1] | 252 014 | 46 170 | 多模态、CV、语音、表格、 强化学习 | 36 | 开放式 | API | TensorFlow,PyTorch,Keras,Caffe,JAX,ONNX,PaddlePaddle,Core ML,FLAIR |
| ModelScope[110] | 955 | 492 | CV、NLP、语音、多模态、 科学计算、语种、其他 | 70 | 开放式 | API,GitHub | TensorFlow,PyTorch,ONNX |
| PaddleHub[111] | 135 | 10 000 | CV、视频、NLP、文心大模型、智 能语音、科学计算、跨模态、强化 学习、量子计算、表格、图神经网 络、时序技术、生物计算、智能推荐 | 14 | 开放式 | API,GitHub | PaddlePaddle |
| TensorFlow Hub[15] | 1 364 | 87 | 图像、文本、语音、视频 | 47 | 封闭式 | API,GitHub | TensorFlow |
| Model Zoo[2] | 1 211 | 0 | CV、NLP、生成式模型、强音频、图、自监督学习、健康和生物医学 | 9 | 封闭式 | GitHub | TensorFlow,PyTorch,Keras,Caffe, JAX,MXNet,Chainer |
| PyTorch Hub[112] | 52 | 0 | 音频、生成式模型、NLP、可脚本化模型、CV | 未知 | 封闭式 | GitHub | PyTorch |
| ONNX Model Zoo[113] | 55 | 0 | CV、NLP、语音 | 10 | 封闭式 | GitHub | ONNX |
| NVIDIA NGC[16] | 560 | 34 | CV、NLP、语音、其他 | 14 | 商业化 | API | PyTorch,TensorFlow |
)], 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/issn1000-1239.202440327, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202440327, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202440327, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202440327, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1753977600000, fullTextJson=null, articleText=null, reference=null)