Article(id=1329458027746406655, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1329457773609332873, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202440487, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1717603200000, receivedDateStr=2024-06-06, revisedDate=1721318400000, revisedDateStr=2024-07-19, acceptedDate=null, acceptedDateStr=null, onlineDate=1794897093949, onlineDateStr=2026-11-17, pubDate=1727712000000, pubDateStr=2024-10-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794897093949, onlineIssueDateStr=2026-11-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794897093949, creator=13701087609, updateTime=1794897093949, updator=13701087609, issue=Issue{id=1329457773609332873, tenantId=1146029695717560320, journalId=1324759914146529478, year='2024', volume='61', issue='10', pageStart='2401', pageEnd='2661', issueExtLink='null', onlineDate='null', pubDate='1727712000000', pubDateStr='2024-10-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794897033359, creator='13701087609', updateTime=1794897033359, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=2607, endPage=2626, ext={EN=ArticleExt(id=1329458029466071296, articleId=1329458027746406655, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Survey of Backdoor Attack and Defense Algorithms Based on Federated Learning, columnId=1329457919336231152, journalTitle=Journal of Computer Research and Development, columnName=Artificial Intelligence Security for Data Elements, runingTitle=null, highlight=null, articleAbstract=
Federated learning is designed for data privacy and data security issues, after a large number of clients are trained locally in a distributed manner, the central server then aggregates the model parameter updates provided by each local client, but the central server is unable to see how these parameters are updated, and this feature creates a serious security issue, i.e., a malicious participant can train a poisoned model and upload the parameters in the local model, and then globally model to introduce backdoor features. In this paper, we focus on the security and robustness research under the scenarios specific to federated learning, i.e., backdoor attack and defense, summarize the scenarios that generate backdoor attacks under federated learning, summarize the latest methods of backdoor attack and defense under federated learning, and compare and analyze the performance of the various attack and defense methods, revealing their advantages and limitations. Finally, we point out various potential directions and new challenges for backdoor attacks and defenses under federated learning.
, authors=Jialang Liu, Yanming Guo*, Mingrui Lao, Tianyuan Yu, Yulun Wu, Yunhao Feng, Jiazhuang Wu, authorsList=Jialang Liu, Yanming Guo, Mingrui Lao, Tianyuan Yu, Yulun Wu, Yunhao Feng, Jiazhuang Wu, authorCompany=null, correspAuthors=Yanming Guo, authorNote=
born in 1999. Master cadidate. His main research interests include federated learning, backdoor attack, and deep learning
born in 1989. Associate professor. His main research interests include deep learning, cross-media information processing, and intelligent adversarial attack
born in 1995, PhD, lecturer. His main research interests include cross-media data analysis, and data security and adversarial attack defense
born in 1992. PhD. His main research interests include computer vision, federated learning, and visual language modeling
born in 1996. PhD candidate. His main research interests include adversarial machine learning, trustworthy AI, and multimodal deep learning
born in 2002. PhD candidate. His main research interests include trustworthy security of artificial intelligence, adversarial robustness, and federated algorithms
born in 2001. Master candidate. His main research interests include adversarial examples and federated learning
, correspAuthorsNote=null, copyrightStatement=Copyright © 2024 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=1329458032163008799, articleId=1329458027746406655, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=基于联邦学习的后门攻击与防御算法综述, columnId=1329457919541752050, journalTitle=计算机研究与发展, columnName=面向数据要素的人工智能安全, runingTitle=null, highlight=null, articleAbstract=
联邦学习旨在解决数据隐私和数据安全问题,大量客户端在本地进行分布式训练后,中央服务器再聚合各本地客户端提供的模型参数更新,但中央服务器无法看到这些参数的具体更新过程,这种特性会带来严重的安全问题,即恶意参与者可以在本地模型中训练中毒模型并上传参数,再在全局模型中引入后门功能. 关注于联邦学习特有场景下的安全性和鲁棒性研究,即后门攻击与防御,总结了联邦学习下产生后门攻击的场景,并归纳了联邦学习下后门攻击和防御的最新方法,对各种攻击和防御方法的性能进行了比较和分析,揭示了其优势和局限. 最后,指出了联邦学习下后门攻击和防御的各种潜在方向和新的挑战.
, authors=刘嘉浪, 郭延明*, 老明瑞, 于天元, 武与伦, 冯云浩, 吴嘉壮, authorsList=刘嘉浪, 郭延明, 老明瑞, 于天元, 武与伦, 冯云浩, 吴嘉壮, authorCompany=null, correspAuthors=郭延明, authorNote=
 |
1999年生. 硕士研究生. 主要研究方向为联邦学习、后门攻击、深度学习 |
 |
1989年生. 副教授. 主要研究方向为深度学习、跨媒体信息处理、智能对抗 |
 |
1995年生. 博士,讲师. 主要研究方向为跨媒体数据分析、数据安全与对抗攻防 |
 |
1992年生. 博士. 主要研究方向为计算机视觉、联邦学习、视觉语言建模 |
 |
1996年生. 博士研究生. 主要研究方向为对抗机器学习、可信人工智能、多模态深度学习 |
 |
2002年生. 博士研究生. 主要研究方向为人工智能置信度的安全性、对抗鲁棒性、联邦算法 |
 |
2001年生. 硕士研究生. 主要研究方向为对抗样本、联邦学习 |
, correspAuthorsNote=
, copyrightStatement=版权所有 © 2024 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=vK7qAi0Vitxf1Ysv/PK3qw==, magXml=05ZAxtwYA3Mqu0XtXOyncQ==, pdfUrl=null, pdf=jyMAprzcdZfa21z9mgiItA==, pdfFileSize=2436586, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=wAcRfG3+M5JOFuHDRUN11w==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=1ugBz0XKb/TP+Vo/zw/HhQ==, mapNumber=null, fund=null)}, authors=[Author(id=1329458034033668388, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liu_1999@nudt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329458034125943078, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, authorId=1329458034033668388, language=EN, stringName=Jialang Liu, firstName=Jialang, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Laboratory for Big Data and Decision (National University of Defense Technology), Changsha 410000, bio={"content":"
born in 1999. Master cadidate. His main research interests include federated learning, backdoor attack, and deep learning
"}, bioImg=null, bioContent=
born in 1999. Master cadidate. His main research interests include federated learning, backdoor attack, and deep learning
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458034188857639, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, authorId=1329458034033668388, language=CN, stringName=刘嘉浪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=大数据与决策实验室(国防科技大学) 长沙 410000, bio={"img":"On6uO3JBy80oYCq33H6q0Q==","content":"
1999年生. 硕士研究生. 主要研究方向为联邦学习、后门攻击、深度学习
"}, bioImg=On6uO3JBy80oYCq33H6q0Q==, bioContent=
1999年生. 硕士研究生. 主要研究方向为联邦学习、后门攻击、深度学习
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458033928810784, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, xref=null, ext=[AuthorCompanyExt(id=1329458033937199393, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, companyId=1329458033928810784, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Laboratory for Big Data and Decision (National University of Defense Technology), Changsha 410000), AuthorCompanyExt(id=1329458033945588002, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, companyId=1329458033928810784, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=大数据与决策实验室(国防科技大学) 长沙 410000)])]), Author(id=1329458034255966505, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=guoyanming@nudt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1329458034327269675, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, authorId=1329458034255966505, language=EN, stringName=Yanming Guo, firstName=Yanming, middleName=null, lastName=Guo, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=Laboratory for Big Data and Decision (National University of Defense Technology), Changsha 410000, bio={"content":"
born in 1989. Associate professor. His main research interests include deep learning, cross-media information processing, and intelligent adversarial attack
"}, bioImg=null, bioContent=
born in 1989. Associate professor. His main research interests include deep learning, cross-media information processing, and intelligent adversarial attack
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458034406961452, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, authorId=1329458034255966505, language=CN, stringName=郭延明, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=大数据与决策实验室(国防科技大学) 长沙 410000, bio={"img":"Nd0zM3al5QcJy2VYEFQFjQ==","content":"
1989年生. 副教授. 主要研究方向为深度学习、跨媒体信息处理、智能对抗
"}, bioImg=Nd0zM3al5QcJy2VYEFQFjQ==, bioContent=
1989年生. 副教授. 主要研究方向为深度学习、跨媒体信息处理、智能对抗
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458033928810784, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, xref=null, ext=[AuthorCompanyExt(id=1329458033937199393, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, companyId=1329458033928810784, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Laboratory for Big Data and Decision (National University of Defense Technology), Changsha 410000), AuthorCompanyExt(id=1329458033945588002, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, companyId=1329458033928810784, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=大数据与决策实验室(国防科技大学) 长沙 410000)])]), Author(id=1329458034478264622, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, 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=1329458034545373488, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, authorId=1329458034478264622, language=EN, stringName=Mingrui Lao, firstName=Mingrui, middleName=null, lastName=Lao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Laboratory for Big Data and Decision (National University of Defense Technology), Changsha 410000, bio={"content":"
born in 1995, PhD, lecturer. His main research interests include cross-media data analysis, and data security and adversarial attack defense
"}, bioImg=null, bioContent=
born in 1995, PhD, lecturer. His main research interests include cross-media data analysis, and data security and adversarial attack defense
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458034620870961, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, authorId=1329458034478264622, language=CN, stringName=老明瑞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=大数据与决策实验室(国防科技大学) 长沙 410000, bio={"img":"sUYTgRbOzN57aU26lRWcmQ==","content":"
1995年生. 博士,讲师. 主要研究方向为跨媒体数据分析、数据安全与对抗攻防
"}, bioImg=sUYTgRbOzN57aU26lRWcmQ==, bioContent=
1995年生. 博士,讲师. 主要研究方向为跨媒体数据分析、数据安全与对抗攻防
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458033928810784, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, xref=null, ext=[AuthorCompanyExt(id=1329458033937199393, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, companyId=1329458033928810784, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Laboratory for Big Data and Decision (National University of Defense Technology), Changsha 410000), AuthorCompanyExt(id=1329458033945588002, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, companyId=1329458033928810784, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=大数据与决策实验室(国防科技大学) 长沙 410000)])]), Author(id=1329458034696368435, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, 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=1329458034759282998, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, authorId=1329458034696368435, language=EN, stringName=Tianyuan Yu, firstName=Tianyuan, middleName=null, lastName=Yu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Laboratory for Big Data and Decision (National University of Defense Technology), Changsha 410000, bio={"content":"
born in 1992. PhD. His main research interests include computer vision, federated learning, and visual language modeling
"}, bioImg=null, bioContent=
born in 1992. PhD. His main research interests include computer vision, federated learning, and visual language modeling
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458034855751991, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, authorId=1329458034696368435, language=CN, stringName=于天元, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=大数据与决策实验室(国防科技大学) 长沙 410000, bio={"img":"Dab5lVdGaieiTee8TftNGA==","content":"
1992年生. 博士. 主要研究方向为计算机视觉、联邦学习、视觉语言建模
"}, bioImg=Dab5lVdGaieiTee8TftNGA==, bioContent=
1992年生. 博士. 主要研究方向为计算机视觉、联邦学习、视觉语言建模
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458033928810784, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, xref=null, ext=[AuthorCompanyExt(id=1329458033937199393, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, companyId=1329458033928810784, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Laboratory for Big Data and Decision (National University of Defense Technology), Changsha 410000), AuthorCompanyExt(id=1329458033945588002, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, companyId=1329458033928810784, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=大数据与决策实验室(国防科技大学) 长沙 410000)])]), Author(id=1329458034922860857, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, 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=1329458034989969723, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, authorId=1329458034922860857, language=EN, stringName=Yulun Wu, firstName=Yulun, middleName=null, lastName=Wu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Laboratory for Big Data and Decision (National University of Defense Technology), Changsha 410000, bio={"content":"
born in 1996. PhD candidate. His main research interests include adversarial machine learning, trustworthy AI, and multimodal deep learning
"}, bioImg=null, bioContent=
born in 1996. PhD candidate. His main research interests include adversarial machine learning, trustworthy AI, and multimodal deep learning
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458035078050108, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, authorId=1329458034922860857, language=CN, stringName=武与伦, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=大数据与决策实验室(国防科技大学) 长沙 410000, bio={"img":"gV7QjFNaxQX3D2cfRyEqCQ==","content":"
1996年生. 博士研究生. 主要研究方向为对抗机器学习、可信人工智能、多模态深度学习
"}, bioImg=gV7QjFNaxQX3D2cfRyEqCQ==, bioContent=
1996年生. 博士研究生. 主要研究方向为对抗机器学习、可信人工智能、多模态深度学习
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458033928810784, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, xref=null, ext=[AuthorCompanyExt(id=1329458033937199393, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, companyId=1329458033928810784, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Laboratory for Big Data and Decision (National University of Defense Technology), Changsha 410000), AuthorCompanyExt(id=1329458033945588002, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, companyId=1329458033928810784, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=大数据与决策实验室(国防科技大学) 长沙 410000)])]), Author(id=1329458035161936190, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, 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=1329458035237433664, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, authorId=1329458035161936190, language=EN, stringName=Yunhao Feng, firstName=Yunhao, middleName=null, lastName=Feng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Laboratory for Big Data and Decision (National University of Defense Technology), Changsha 410000, bio={"content":"
born in 2002. PhD candidate. His main research interests include trustworthy security of artificial intelligence, adversarial robustness, and federated algorithms
"}, bioImg=null, bioContent=
born in 2002. PhD candidate. His main research interests include trustworthy security of artificial intelligence, adversarial robustness, and federated algorithms
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458035317125441, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, authorId=1329458035161936190, language=CN, stringName=冯云浩, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=大数据与决策实验室(国防科技大学) 长沙 410000, bio={"img":"yeevOLchA4QxYNy8MIecDQ==","content":"
2002年生. 博士研究生. 主要研究方向为人工智能置信度的安全性、对抗鲁棒性、联邦算法
"}, bioImg=yeevOLchA4QxYNy8MIecDQ==, bioContent=
2002年生. 博士研究生. 主要研究方向为人工智能置信度的安全性、对抗鲁棒性、联邦算法
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458033928810784, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, xref=null, ext=[AuthorCompanyExt(id=1329458033937199393, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, companyId=1329458033928810784, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Laboratory for Big Data and Decision (National University of Defense Technology), Changsha 410000), AuthorCompanyExt(id=1329458033945588002, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, companyId=1329458033928810784, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=大数据与决策实验室(国防科技大学) 长沙 410000)])]), Author(id=1329458035392622915, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329458035472314693, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, authorId=1329458035392622915, language=EN, stringName=Jiazhuang Wu, firstName=Jiazhuang, middleName=null, lastName=Wu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Laboratory for Big Data and Decision (National University of Defense Technology), Changsha 410000, bio={"content":"
born in 2001. Master candidate. His main research interests include adversarial examples and federated learning
"}, bioImg=null, bioContent=
born in 2001. Master candidate. His main research interests include adversarial examples and federated learning
, aboutCorrespAuthor=null), CN=AuthorExt(id=1329458035547812166, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, authorId=1329458035392622915, language=CN, stringName=吴嘉壮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=大数据与决策实验室(国防科技大学) 长沙 410000, bio={"img":"psZAOw35MF9Tnz3rX0FnaQ==","content":"
2001年生. 硕士研究生. 主要研究方向为对抗样本、联邦学习
"}, bioImg=psZAOw35MF9Tnz3rX0FnaQ==, bioContent=
2001年生. 硕士研究生. 主要研究方向为对抗样本、联邦学习
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329458033928810784, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, xref=null, ext=[AuthorCompanyExt(id=1329458033937199393, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, companyId=1329458033928810784, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Laboratory for Big Data and Decision (National University of Defense Technology), Changsha 410000), AuthorCompanyExt(id=1329458033945588002, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, companyId=1329458033928810784, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=大数据与决策实验室(国防科技大学) 长沙 410000)])])], keywords=[Keyword(id=1329458035648475463, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, orderNo=1, keyword=federated learning), Keyword(id=1329458035719778632, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, orderNo=2, keyword=backdoor attack), Keyword(id=1329458035774304585, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, orderNo=3, keyword=backdoor defense), Keyword(id=1329458035833024842, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, orderNo=4, keyword=data privacy), Keyword(id=1329458035887550795, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, orderNo=5, keyword=data security), Keyword(id=1329458035946271052, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, orderNo=1, keyword=联邦学习), Keyword(id=1329458036013379917, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, orderNo=2, keyword=后门攻击), Keyword(id=1329458036101460302, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, orderNo=3, keyword=后门防御), Keyword(id=1329458036168569167, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, orderNo=4, keyword=数据隐私), Keyword(id=1329458036231483728, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, orderNo=5, keyword=数据安全)], refs=[Reference(id=1329458040723583346, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, 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=Prakash S, Hashemi H, Wang Yongqin, et al. Secure and fault tolerant decentralized learning[J]. arXiv preprint, arXiv: 2010.07541, 2020, articleTitle=null, refAbstract=null), Reference(id=1329458040790692211, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, 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=周俊,方国英,吴楠. 联邦学习安全与隐私保护研究综述[J]. 西华大学学报:自然科学版,2020,39(4):9−17. 7, articleTitle=null, refAbstract=null), Reference(id=1329458040866189684, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Jun, Fang Guoying, Wu Nan, Survey on security and privacy-preserving in federated learnin[J]. Journal of Xihua University(Nature Science Edition), 2020, 39(4): 9−17. 7 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329458040937492853, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=陈兵,成翔,张佳乐,等. 联邦学习安全与隐私保护综述[J]. 南京航空航天大学学报,2020,52(5):675−684, articleTitle=null, refAbstract=null), Reference(id=1329458040996213110, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Bing, Cheng Xiang, Zhang Jiale, et al. Survey of security and privacy in fedrated learnin[J]. Journal of Nanjing University of Aeronautics& Astronautic, 2020, 52(5): 675−684 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329458041050739063, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=高莹,陈晓峰,张一余,等. 联邦学习系统攻击与防御技术研究综述[J]. 计算机学报,2023,46(9):1781−1805, articleTitle=null, refAbstract=null), Reference(id=1329458041113653624, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=Gao Ying, Chne Xiaofeng, Zhang Yiyu, et al. Survey of attack and defense techniques for federated learning systems[J], Chinese Journal of Computers, 2023, 46(9): 1781−1805 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329458042724266362, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=肖雄,唐卓,肖斌,等. 联邦学习的隐私保护与安全防御研究综述[J]. 计算机学报,2023,46(5):1019−1044, articleTitle=null, refAbstract=null), Reference(id=1329458042799763835, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Xiao Xiong, Tang Zhuo, Xiao Bin, et al. A Survey on privacy and security issues in federated learning[J], Chinese Journal of Computers, 2023, 46(5): 1019−1044 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329458042896232828, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Rui, Xing Pengwei, Deng Zichao, et al. Federated graph neural networks: Overview, techniques and challenges[J]. arXiv preprint, arXiv: 2202.07256, 2023, articleTitle=null, refAbstract=null), Reference(id=1329458042975924605, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Yifei, Zeng Dun, Luo Jinglong, et al. A survey of trustworthy federated learning with perspectives on security, robustness and privacy[C]//Proc of the ACM Web Conf. New York: ACM, 2023: 1167−1176, articleTitle=null, refAbstract=null), Reference(id=1329458043072393598, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Asadullah T, Mohamed A, Farag S, et al. Trustworthy federated learning: A survey[J]. arXiv preprint, arXiv: 2305.11537, 2023, articleTitle=null, refAbstract=null), Reference(id=1329458043160473983, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Qiang, Liu Yang, Cheng Yong, et al. Federated Learning: Synthesis Lectures on Artificial Intelligence and Machine Learning[M]. San Rafael, CA: Morgan & Claypool, 2019, 13: 1−207, articleTitle=null, refAbstract=null), Reference(id=1329458043235971456, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Qiang,Liu Yang,Cheng Yong,et al. Federated Learning:Synthesis Lectures on Artificial Intelligence and Machine Learning[M]. San Rafael, CA: Morgan & Claypool, 2019,13:1−207, articleTitle=null, refAbstract=null), Reference(id=1329458043311468929, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Mothukuri V, Parizi R M, Pouriyeh S, et al. A survey on security and privacy of federated learning[J]. Future Generation Computer Systems, 2021, 115: 619−640, articleTitle=null, refAbstract=null), Reference(id=1329458043479241090, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Blanchard P, El Mhamdi E M, Guerraoui R, et al. Machine learning with adversaries: Byzantine tolerant gradient descent[J]. Advances in Neural Information Processing Systems, 2017, 30: 119−129, articleTitle=null, refAbstract=null), Reference(id=1329458043554738563, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=El M, Rachid G, and Sébastien R, et al. The hidden vulnerability of distributed learning in Byzantium[C]//Proc of Int Conf on Machine Learning. New York: PMLR, 2018: 3521–3530, articleTitle=null, refAbstract=null), Reference(id=1329458043621847428, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Leslie Lamport, Robert Shostak, Marshall Pease. The Byzantine generals problem[J]. In Concurrency: The Works of Leslie Lamport. 2022: 203–226, articleTitle=null, refAbstract=null), Reference(id=1329458043688956293, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Shen S, Tople S, Saxena P. Auror: Defending against poisoning attacks in collaborative deep learning systems[C]//Proc of the 32nd Annual Conf on Computer Security Applications. Los Angeles: ACM, 2016: 508−519, articleTitle=null, refAbstract=null), Reference(id=1329458043777036678, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Fang Minghong, Cao Xiaoyu, Jia Jinyuan, et al. Local model poisoning attacks to {Byzantine-Robust} federated learning[C]//Proc of the 29th USENIX Security Symp (USENIX Security 20). Berkeley CA: USENIX Association, 2020: 1605−1622, articleTitle=null, refAbstract=null), Reference(id=1329458043844145543, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Damaskinos G, El-Mhamdi E M, Guerraoui R, et al. Aggregathor: Byzantine machine learning via robust gradient aggregation[J]. Proceedings of Machine Learning and Systems, 2019, 1: 81−106, articleTitle=null, refAbstract=null), Reference(id=1329458043902865800, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Chen, Liu Yuchen, Ma Xingjun, et al. Calfat: Calibrated federated adversarial training with label skewness[J]. Advances in Neural Information Processing Systems, 2022, 35: 3569−3581, articleTitle=null, refAbstract=null), Reference(id=1329458044028694921, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Doan B G, Abbasnejad E, Ranasinghe D C. Februus: Input purification defense against trojan attacks on deep neural network systems[C]//Proc of the 36th Annual Computer Security Applications Conf. Los Angeles: ACM, 2020: 897-912, articleTitle=null, refAbstract=null), Reference(id=1329458044091609482, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Nuria R, Daniel J, M. Victoria L, et al. Survey on federated learning threats: Concepts, taxonomy on attacks and defences, experimental study and challenges[J]. Information Fusion, 2023, 90: 148−173, articleTitle=null, refAbstract=null), Reference(id=1329458044246798731, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Bhagoji A N, Chakraborty S, Mittal P, et al. Analyzing federated learning through an adversarial lens[C]//Proc of Int Conf on Machine Learning. New York: PMLR, 2019: 634−643, articleTitle=null, refAbstract=null), Reference(id=1329458044326490508, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Bagdasaryan E, Veit A, Hua Yiqing, et al. How to backdoor federated learning[C]//Proc of Int Conf on Artificial Intelligence and Statistics. New York: PMLR, 2020: 2938−2948, articleTitle=null, refAbstract=null), Reference(id=1329458044385210765, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Barreno M, Nelson B, Sears R. et al. Can machine learning be secure? [C]//Proc of the 2006 ACM Symp on Information, Computer and Communications Security. New York: ACM, 2006: 16-25, articleTitle=null, refAbstract=null), Reference(id=1329458044460708238, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Doshi K, Yilmaz Y. Federated learning-based driver activity recognition for edge devices[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2022: 3338−3346, articleTitle=null, refAbstract=null), Reference(id=1329458044536205712, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Dai Yanbo, Li Songzi. Chameleon: Adapting to peer images for planting durable backdoors in federated learning[C]//Proc of Int Conf on Machine Learning. New York: PMLR, 2023: 6712−6725, articleTitle=null, refAbstract=null), Reference(id=1329458044607508881, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Fung C, Yoon C J M, Beschastnikh I. The limitations of federated learning in sybil settings[C]//Proc of 23rd Int Symp on Research in Attacks, Intrusions and Defenses (RAID 2020). San Sebastian: USENIX, 2020: 301−316, articleTitle=null, refAbstract=null), Reference(id=1329458044678812050, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Bernstein J, Zhao J, Azizzadenesheli K, et al. signSGD with majority vote is communication efficient and fault tolerant[J]. arXiv preprint, arXiv: 1810.05291, 2018, articleTitle=null, refAbstract=null), Reference(id=1329458044745920915, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Ruiliang, Park J M J, Bian Kaigui. Robustness against Byzantine failures in distributed spectrum sensing[J]. Computer Communications, 2012, 35(17): 2115−2124, articleTitle=null, refAbstract=null), Reference(id=1329458044829806997, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhong Haoti, Liao Cong, Squicciarini A C, et al. Backdoor embedding in convolutional neural network models via invisible perturbation[C]//Proc of the ACM Conf on Data and Application Security and Privacy. New York: ACM, 2020: 97−108, articleTitle=null, refAbstract=null), Reference(id=1329458044972413334, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Cheng, Kailkhura B, Goldhahn R, et al. Certifiably-robust federated adversarial learning via randomized smoothing[C]//Proc of 2021 IEEE 18th Int Conf on Mobile Ad Hoc and Smart Systems (MASS). Piscataway, NJ: IEEE, 2021: 173−179, articleTitle=null, refAbstract=null), Reference(id=1329458045060493719, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Saha A, Subramanya A, Pirsiavash H. Hidden trigger backdoor attacks[C]//Proc of the AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2020, 34(7): 11957−11965, articleTitle=null, refAbstract=null), Reference(id=1329458045135991192, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Enthoven D, Al-Ars Z. An overview of federated deep learning privacy attacks and defensive strategies[J]. Federated Learning Systems: Towards Next-Generation AI, 2021: 173−196, articleTitle=null, refAbstract=null), Reference(id=1329458045215682969, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Y, Jiang Y, Li Z, et al. Backdoor learning: A survey[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 35(1): 5−22, articleTitle=null, refAbstract=null), Reference(id=1329458045320540570, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Sun Ziteng, Peter K, Ananda T, et al. Can you really backdoor federated learning?[J]. arXiv preprint, arXiv: 1911.07963, 2019, articleTitle=null, refAbstract=null), Reference(id=1329458045379260827, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Kota Y, Takeshi F. Disabling backdoor and identifying poison data by using knowledge distillation in backdoor attacks on deep neural networks[C]//Proc of the 13th ACM Workshop on Artificial Intelligence and Security. New York: ACM, 2020: 117–127, articleTitle=null, refAbstract=null), Reference(id=1329458045458952604, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Nguyen T D, Rieger P, De V, et al. {FLAME}: Taming backdoors in federated learning[C]//Proc of the 31st USENIX Security Symp (USENIX Security 22). Berkeley, CA: USENIX Association, 2022: 1415−1432, articleTitle=null, refAbstract=null), Reference(id=1329458045551227293, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Douceur J R. The sybil attack[C]//Proc of Int Workshop on Peer-to-Peer Systems. Berlin: Springer, 2002: 251−260, articleTitle=null, refAbstract=null), Reference(id=1329458047166034335, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Hanxun, Ma Xingjun, Sarah E, et al. Distilling cognitive backdoor patterns within an image[J]. arXiv preprint, arXiv: 2301.10908, 2023, articleTitle=null, refAbstract=null), Reference(id=1329458047342195104, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Ning, Xiao Yang, Chen Yimin, et al. flare: Defending federated learning against model poisoning attacks via latent space representations[C]//Proc of 2022 ACM on Asia Conf on Computer and Communications Security. New York: ACM, 2022: 946–958, articleTitle=null, refAbstract=null), Reference(id=1329458047472218529, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Gu T, Dolan-Gavitt B, Garg S. Badnets: Identifying vulnerabilities in the machine learning model supply chain[J]. arXiv preprint, arXiv: 1708.06733, 2017, articleTitle=null, refAbstract=null), Reference(id=1329458047543521698, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Alberti M, Pondenkandath V, Wursch M, et al. Are You Tampering with My Data?[J]. arXiv preprint, arXiv: 1808.04866, 2018, articleTitle=null, refAbstract=null), Reference(id=1329458047765819811, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Xinyun, Liu Chang, Li Bo, et al. Targeted backdoor attacks on deep learning systems using data poisoning[J]. arXiv preprint, arXiv: 1712.05526, 2017, articleTitle=null, refAbstract=null), Reference(id=1329458047900037541, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Barni M, Kallas K, Tondi B. A New backdoor attack in CNNS by training set corruption without label poisoning[J]. arXiv preprint, arXiv: 2304.02643, 2023, articleTitle=null, refAbstract=null), Reference(id=1329458048017478054, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Yunfei, Ma Xingjun, Bailey J, et al. Reflection backdoor: A natural backdoor attack on deep neural networks[C]//Proc of the European Conf on Computer Vision. Glasgow, Berlin: Springer, 2020: 182−199, articleTitle=null, refAbstract=null), Reference(id=1329458048181055911, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Madry A, Makelov A, Schmidt L, et al. Towards deep learning models resistant to adversarial attacks[J]. arXiv preprint, arXiv: 1706.06083, 2017, articleTitle=null, refAbstract=null), Reference(id=1329458048281719208, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Quiring E, Rieck K. Backdooring and poisoning neural networks with image-scaling attacks[C]//Proc of the IEEE Security and Privacy Workshops. Piscataway, NJ: IEEE, 2020: 41−47, articleTitle=null, refAbstract=null), Reference(id=1329458048390771113, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Nguyen T A, Tran A. Input-aware dynamic backdoor attack[C]//Proc of the Advances in Neural Information Processing Systems. Online, Vancouver: NeurIPS, 2020, 33: 3454−3464, articleTitle=null, refAbstract=null), Reference(id=1329458048462074282, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Yuezun, Li Yiming, Wu Baoyuan, et al. Invisible backdoor attack with sample-specific triggers[C]//Proc of the IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2021: 16463−16472, articleTitle=null, refAbstract=null), Reference(id=1329458048533377451, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Salem A, Wen R, Backes M, et al. Dynamic backdoor attacks against machine learning models[C]//Proc of the IEEE European Symp on Security and Privacy. Piscataway, NJ: IEEE, 2022: 703−718, articleTitle=null, refAbstract=null), Reference(id=1329458048634040748, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Shafahi A, Huang W, Najibi M, et al. Poison frogs! targeted clean-label poisoning attacks on neural networks[J]. arXiv preprint, arXiv: 2009.03561, 2020, articleTitle=null, refAbstract=null), Reference(id=1329458048713732525, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Chen, Huang W, Li Hengduo, et al. Transferable clean-label poisoning attacks on deep neural nets[C]//Proc of the Int Conf on Machine Learning. New York: PMLR, 2019: 7614−7623, articleTitle=null, refAbstract=null), Reference(id=1329458048785035694, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=Gao Yinghua, Li Yiming, Zhu Linghui, et al. Not all samples are born equal: Towards effective clean-label backdoor attacks[J]. Pattern Recognition, 2023, 139 (Special Issue): 109512, articleTitle=null, refAbstract=null), Reference(id=1329458048902476207, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Junyu, Xu Lei, Liu Yingqi, et al. Composite backdoor attack for deep neural network by mixing existing benign features[C]//Proc of the ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2020: 113−131, articleTitle=null, refAbstract=null), Reference(id=1329458049015722416, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Yingqi, Ma Shiqing, Aafer Y, et al. Trojaning attack on neural networks[C]//Proc of the Annual Network and Distributed System Security Symp. San Diego, USA: Internet Society, 2018: 1−15, articleTitle=null, refAbstract=null), Reference(id=1329458049091219889, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=58, authorNames=null, journalName=null, refType=null, unstructuredReference=Rakin A S, He Zhezhi, Fan Deliang. Tbt: Targeted neural network attack with bit Trojan[C]//Proc of the IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 13195−13204, articleTitle=null, refAbstract=null), Reference(id=1329458049154134450, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=55, rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=Dumford J, Scheirer W. Backdooring convolutional neural networks via targeted weight perturbations[C]//Proc of the IEEE Int Joint Conf on Biometrics. Piscataway, NJ: IEEE, 2020: 1−9, articleTitle=null, refAbstract=null), Reference(id=1329458049217049011, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=56, rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=Hong S, Carlini N, Kurakin A. Handcrafted backdoors in deep neural networks[J]. Advances in Neural Information Processing Systems, 2022, 35: 8068−8080, articleTitle=null, refAbstract=null), Reference(id=1329458049284157876, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=57, rfOrder=61, authorNames=null, journalName=null, refType=null, unstructuredReference=Zou Minghui, Yang Shi, Wang Chengliang, et al. Potrojan: Powerful neural-level trojan designs in deep learning models[J]. arXiv preprint, arXiv: 1802.03043, 2018, articleTitle=null, refAbstract=null), Reference(id=1329458049426764213, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=58, rfOrder=62, authorNames=null, journalName=null, refType=null, unstructuredReference=Salem A, Backes M, Zhang Y. Don’t trigger me! a triggerless backdoor attack against deep neural networks[J]. arXiv preprint, arXiv: 2010.03282, 2020, articleTitle=null, refAbstract=null), Reference(id=1329458049485484470, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=59, rfOrder=63, 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 ACM SIGSAC Conf on Computer and Communications Security. New York: ACM, 2019: 2041−2055, articleTitle=null, refAbstract=null), Reference(id=1329458049548399031, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=60, rfOrder=64, authorNames=null, journalName=null, refType=null, unstructuredReference=Vale T, Stacey T, Mehmet E, et al. Data poisoning attacks against federated learning systems[C]//Proc of Computer Security–ESORICS 2020: 25th European Symposium on Research in Computer Security, ESORICS 2020. Berlin: Springer, 2021: 480–501, articleTitle=null, refAbstract=null), Reference(id=1329458049615507896, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=61, rfOrder=65, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Hengtong, Zheng Tianhang, Gao Jing, et al. Data poisoning attack against knowledge graph embedding[J]. arXiv preprint, arXiv: 1904.12052, 2019, articleTitle=null, refAbstract=null), Reference(id=1329458049682616761, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=62, rfOrder=66, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Shuwen, Luo Ge, Wei Ping, et al. Image-imperceptible backdoor attacks[J]. Journal of Image and Graphics, 2023, 28(3): 864−877, articleTitle=null, refAbstract=null), Reference(id=1329458049783280058, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=63, rfOrder=67, authorNames=null, journalName=null, refType=null, unstructuredReference=Sun W, Jiang X, Dou S, et al. Invisible backdoor attack with dynamic triggers against person re-identification[J]. IEEE Transactions on Information Forensics and Security, 2023, 18: 1653−1665, articleTitle=null, refAbstract=null), Reference(id=1329458049850388923, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=64, rfOrder=68, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Yao, Wu Jun, He Jingrui. Adversarially robust federated learning for neural networks[C]//Proc of Int Conf on ICLR. Washington DC: IEEE, 2021: 105−116, articleTitle=null, refAbstract=null), Reference(id=1329458049909109180, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=64, rfOrder=69, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Yao,Wu Jun,He Jingrui. Adversarially robust federated learning for neural networks[C]//Proc of Int Conf on ICLR. Washington DC: IEEE, 2021:105−116, articleTitle=null, refAbstract=null), Reference(id=1329458049967829437, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=65, rfOrder=70, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Jiale, Chen Bing, Cheng Xiang , et al. PoisonGAN: Generative poisoning attacks against federated learning in edge computing systems[J]. IEEE Internet of Things Journal, 2021, 8(5): 3310−3322, articleTitle=null, refAbstract=null), Reference(id=1329458050039132606, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=66, rfOrder=71, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Kaidi, Liu Sijia, Chen Pinyu, et al. Defending against backdoor attack on deep neural networks[J]. arXiv preprint, arXiv: 2002.12162, 2020, articleTitle=null, refAbstract=null), Reference(id=1329458051595219391, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=67, rfOrder=72, authorNames=null, journalName=null, refType=null, unstructuredReference=Cheng H, Yan T, Shan H. On the trade-off between adversarial and backdoor robustness[J]. Advances in Neural Information Processing Systems, 2020, 33: 11973−11983, articleTitle=null, refAbstract=null), Reference(id=1329458051683299776, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=68, rfOrder=73, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Xingchen, Xu Ming, Wu Yiming, et al. Deep model poisoning attack on federated learning[J]. Future Internet, 2021, 13(3): 73, articleTitle=null, refAbstract=null), Reference(id=1329458051754602946, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=69, rfOrder=74, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Zhengming, Ashwinee P, Song Linyue, et al. Neurotoxin: Durable backdoors in federated learning[C]//Proc of Int Conf on Machine Learning. New York: PMLR, 2022: 26429−26446, articleTitle=null, refAbstract=null), Reference(id=1329458051821711811, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=70, rfOrder=75, authorNames=null, journalName=null, refType=null, unstructuredReference=Sun Y, Ochiai H, Sakuma J. Semi-targeted model poisoning attack on federated learning via backward error analysis[C]//Proc of 2022 Int Joint Conf on Neural Networks (IJCNN). Piscataway, NJ: IEEE, 2022: 1−8, articleTitle=null, refAbstract=null), Reference(id=1329458051893014980, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=71, rfOrder=76, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Haonan, Zhong Yongchao, Yang Bo, et al. An overview of sybil attack detection mechanisms in vfc[C]//Proc of 2022 52nd Annual IEEE/IFIP Int Conf on Dependable Systems and Networks Workshops (DSN-W). Piscataway, NJ: IEEE, 2022, 117–122, articleTitle=null, refAbstract=null), Reference(id=1329458051964318150, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=72, rfOrder=77, authorNames=null, journalName=null, refType=null, unstructuredReference=Zeng Yi, Chen Si, Won P, et al. Adversarial unlearning of backdoors via implicit hypergradient[J]. arXiv preprint, arXiv: 2110.03735, 2021, articleTitle=null, refAbstract=null), Reference(id=1329458052023038407, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=73, rfOrder=78, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Chen, Huang R, Li Hengduo, et al. Transferable clean-label poisoning attacks on deep neural nets[C]//Proc of Int Confon machine learning. New York: PMLR, 2019: 7614−7623, articleTitle=null, refAbstract=null), Reference(id=1329458052106924488, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=74, rfOrder=79, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Chen, Huang W R, Li Hengduo, et al. Transferable clean-label poisoning attacks on deep neural nets[C]//Proc of the 36th Int Conf on Machine Learning. Long Beach: PMLR, 2019: 7614-7623, articleTitle=null, refAbstract=null), Reference(id=1329458052169839049, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=75, rfOrder=80, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Bolun, Yao Yuanshun, Shan S, et al. Neural cleanse: Identifying and mitigating backdoor attacks in neural networks[C]//Proc of 2019 IEEE Symp on Security and Privacy (SP). Piscataway, NJ: IEEE, 2019, 9707–9723, articleTitle=null, refAbstract=null), Reference(id=1329458052232753610, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=76, rfOrder=81, authorNames=null, journalName=null, refType=null, unstructuredReference=Xie Chulin, Chen Minghao, Chen Pinyu, et al. Crfl: Certifiably robust federated learning against backdoor attacks[C]//Proc of Int Conf on Machine Learning, New York: PMLR, 2021: 11372–11382, articleTitle=null, refAbstract=null), Reference(id=1329458052304056779, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=77, rfOrder=82, authorNames=null, journalName=null, refType=null, unstructuredReference=Andreina S, Marson G A, Möllering H, et al. BaFFle: Backdoor detection via feedback-based federated learning[C]//Proc of 2021 IEEE 41st Int Conf on Distributed Computing Systems (ICDCS). Piscataway, NJ: IEEE, 2021: 852−863, articleTitle=null, refAbstract=null), Reference(id=1329458052392137164, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=78, rfOrder=83, authorNames=null, journalName=null, refType=null, unstructuredReference=Razmi F, Lou Jian, Li Xiong. Does differential privacy prevent backdoor attacks in practice?[C]//Proc of IFIP Annual Conf on Data and Applications Security and Privacy. Cham: Springer, 2024: 320−340, articleTitle=null, refAbstract=null), Reference(id=1329458052467634637, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=79, rfOrder=84, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Zaixi, Cao Xiaoyu, Jia Jinyuan, et al. FL detector: Defending federated learning against model poisoning attacks via detecting malicious clients[C]//Proc of the 28th ACM SIGKDD Conf on Knowledge Discovery and Data Mining. New York: ACM, 2022: 2545–2555, articleTitle=null, refAbstract=null), Reference(id=1329458052534743502, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=80, rfOrder=85, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Jie, Li Bo, Chen Chen, et al. Delving into the adversarial robustness of federated learning[C]//Proc of the AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI 2023, 37(9): 11245−11253, articleTitle=null, refAbstract=null), Reference(id=1329458052601852367, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=81, rfOrder=86, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu C, Wu F, Cao Y, et al. Fedgnn: Federated graph neural network for privacy-preserving recommendation[J]. arXiv preprint, arXiv: 2102.04925, 2021, articleTitle=null, refAbstract=null), Reference(id=1329458052673155536, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=82, rfOrder=87, authorNames=null, journalName=null, refType=null, unstructuredReference=Xie Cong, Koyejo O, Gupta I. Fall of empires: Breaking byzantine-tolerant sgd by inner prod-uct manipulation[C]//Proc of Uncertainty in Artificial Intelligence. New York: PMLR, 2020, 261–270, articleTitle=null, refAbstract=null), Reference(id=1329458052761235921, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=83, rfOrder=88, authorNames=null, journalName=null, refType=null, unstructuredReference=Zizzo G, Rawat A, Sinn M, et al. Fat: Federated adversarial training[J]. arXiv preprint, arXiv: 2012.01791, 2020, articleTitle=null, refAbstract=null), Reference(id=1329458052828344786, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=84, rfOrder=89, authorNames=null, journalName=null, refType=null, unstructuredReference=Nguyen T, Phillip R, Mohammad H, et al. flguard: Secure and private federated learning[J]. Crytography and Security, (Preprint), 2022. https://arxiv.org/abs/2101.02281, articleTitle=null, refAbstract=null), Reference(id=1329458052895453651, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=85, rfOrder=90, authorNames=null, journalName=null, refType=null, unstructuredReference=Jebreel N M, Josep Domingo-Ferrer J, Sánchez D, et al. Defending against the label-flipping attack in federated learning[J]. arXiv: 2207.01982v1, articleTitle=null, refAbstract=null), Reference(id=1329458052962562516, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=85, rfOrder=91, authorNames=null, journalName=null, refType=null, unstructuredReference=Jebreel N M, Josep Domingo-Ferrer J, Sánchez D, et al. Defending against the label-flipping attack in federated learning[J]. arXiv: 2207.01982v1, articleTitle=null, refAbstract=null), Reference(id=1329458053029671381, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=86, rfOrder=92, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Liuwan, Ning Rui, Wang Cong, et al. Gangsweep: Sweep out neural backdoors by gan[C]//Proc of the 28th ACM Int Conf on Multimedia. New York: ACM, 2020: 3173−3181, articleTitle=null, refAbstract=null), Reference(id=1329458053096780246, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=87, rfOrder=93, authorNames=null, journalName=null, refType=null, unstructuredReference=Ahmed S, Rui W, Michael B, et al. Dynamic backdoor attacks against machine learning models[C]//Proc of the 7th European Symp on Security and Privacy (EuroS&P). Piscataway, NJ: IEEE, 2023: 703–718, articleTitle=null, refAbstract=null), Reference(id=1329458053155500503, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=88, rfOrder=94, authorNames=null, journalName=null, refType=null, unstructuredReference=Unterluggauer T, Harris A, Constable S, et al. Chameleon cache: Approximating fully associative caches with random replacement to prevent contention-based cache attacks[C]//Proc of IEEE Int Symp on Secure and Private Execution Environment Design (SEED). Piscataway, NJ: IEEE, 2022: 13−24, articleTitle=null, refAbstract=null), Reference(id=1329458053218415064, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=89, rfOrder=95, authorNames=null, journalName=null, refType=null, unstructuredReference=Tolpegin V, Truex S, Gursoy M E, et al. Data poisoning attacks against federated learning systems[C]//Proc of Computer Security–ESORICS 2020: 25th European Symp on Research in Computer Security, ESORICS 2020. Guildford, UK: Springer, 2021: 480–501, articleTitle=null, refAbstract=null), Reference(id=1329458053289718233, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=90, rfOrder=96, authorNames=null, journalName=null, refType=null, unstructuredReference=Nguyen T D, Rieger P, De V, et al. {FLAME}: Taming backdoors in federated learning[C]//Proc of the 31st USENIX Security Symp (USENIX Security 22). Berkeley, California: USENIX Association, 2022: 1415-1432, articleTitle=null, refAbstract=null), Reference(id=1329458053348438490, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=90, rfOrder=97, authorNames=null, journalName=null, refType=null, unstructuredReference=Nguyen T D,Rieger P,De V,et al. {FLAME}:Taming backdoors in federated learning[C]//Proc of the 31st USENIX Security Symp (USENIX Security 22). Berkeley, California: USENIX Association, 2022: 1415-1432, articleTitle=null, refAbstract=null), Reference(id=1329458053440713179, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=91, rfOrder=98, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Yunfei, Ma Xingjun, Bailey J, et al. Reflection backdoor: A natural backdoor attack on deep neural networks[C]//Proc of the European Conf on Computer Vision. Berlin: Springer, 2020: 182−199, articleTitle=null, refAbstract=null), Reference(id=1329458053516210652, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=92, rfOrder=99, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Mingqing, Suresh A T, Mathews R, et al. Federated learning of n-gram language models[J]. arXiv preprint, arXiv: 1910.03432, 2019, articleTitle=null, refAbstract=null), Reference(id=1329458053579125213, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=93, rfOrder=100, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Yuchen, He Chaoyang, Zeng Zihang, et al. Fednlp: A research platform for federated learning in natural language processing[J]. arXiv preprint, arXiv: 2104.08815, 2021, articleTitle=null, refAbstract=null), Reference(id=1329458053654622686, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=94, rfOrder=101, authorNames=null, journalName=null, refType=null, unstructuredReference=Gu Tianyu, Dolan-Gavitt B, Garg S. Badnets: Identifying vulnerabilities in the machine learning model supply chain[J]. arXiv preprint, arXiv: 1708.06733, 2017, articleTitle=null, refAbstract=null), Reference(id=1329458053717537247, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=95, rfOrder=102, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Jierui, Du Min, Liu Jian. Free-riders in federated learning: Attacks and defenses[J]. arXiv preprint, arXiv: 1911.12560, 2019, articleTitle=null, refAbstract=null), Reference(id=1329458053776257504, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=96, rfOrder=103, authorNames=null, journalName=null, refType=null, unstructuredReference=Lan H, Gu J, Torr P, et al. Influencer backdoor attack on semantic segmentation[J]. arXiv preprint, arXiv: 2303.12054, 2023, articleTitle=null, refAbstract=null), Reference(id=1329458053834977761, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=97, rfOrder=104, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Linyuan, Ding Guoru, Wu Qihui, et al. Byzantine attack and defense in cognitive radio networks: A survey[J]. IEEE Communications Surveys & Tutorials, 2015, 17(3): 1342−1363, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1329458033928810784, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, xref=null, ext=[AuthorCompanyExt(id=1329458033937199393, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, companyId=1329458033928810784, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Laboratory for Big Data and Decision (National University of Defense Technology), Changsha 410000), AuthorCompanyExt(id=1329458033945588002, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, companyId=1329458033928810784, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=大数据与决策实验室(国防科技大学) 长沙 410000)])], figs=[ArticleFig(id=1329458036348924242, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, label=Figure 1, caption=
Federal learning architecture and security issues, figureFileSmall=e06fItKI4pMp21MhlXBrgQ==, figureFileBig=wAcRfG3+M5JOFuHDRUN11w==, tableContent=null), ArticleFig(id=1329458036411838803, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, label=图1, caption=
联邦学习架构及安全性问题, figureFileSmall=e06fItKI4pMp21MhlXBrgQ==, figureFileBig=wAcRfG3+M5JOFuHDRUN11w==, tableContent=null), ArticleFig(id=1329458036587999572, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, label=Figure 2, caption=
Classification of federated learning, figureFileSmall=tlqi4ziWmZjPltcKATuCTg==, figureFileBig=z7RIpodlPdnRb7cbSMECRA==, tableContent=null), ArticleFig(id=1329458038269915477, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, label=图2, caption=
联邦学习分类, figureFileSmall=tlqi4ziWmZjPltcKATuCTg==, figureFileBig=z7RIpodlPdnRb7cbSMECRA==, tableContent=null), ArticleFig(id=1329458038345412950, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, label=Figure 3, caption=
Speed limit signs have been injected with “backdoors”, figureFileSmall=jXmbCr2HIxcOboitJLp5OQ==, figureFileBig=ITj0hHPsJlFdmWpKIMZd1g==, tableContent=null), ArticleFig(id=1329458038408327511, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, label=图3, caption=
限速牌插入“后门”, figureFileSmall=jXmbCr2HIxcOboitJLp5OQ==, figureFileBig=ITj0hHPsJlFdmWpKIMZd1g==, tableContent=null), ArticleFig(id=1329458038483824984, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, label=Figure 4, caption=
MNIST injected with backdoor and model training process, figureFileSmall=LMeIw7dLn+46MyBSdn9YoQ==, figureFileBig=/p3tKJSB7ZHiEe7eVclj0A==, tableContent=null), ArticleFig(id=1329458038567711065, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, label=图4, caption=
在MNIST上注入后门及模型训练过程, figureFileSmall=LMeIw7dLn+46MyBSdn9YoQ==, figureFileBig=/p3tKJSB7ZHiEe7eVclj0A==, tableContent=null), ArticleFig(id=1329458038634819930, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, label=Figure 5, caption=
Connection of backdoor attacks and defense scenarios, figureFileSmall=uh0xWSG2YipG3gdEbjFGSQ==, figureFileBig=4rnmnJdvsDnp4QMjlrP0Bg==, tableContent=null), ArticleFig(id=1329458038743871835, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, label=图5, caption=
后门攻击与防御场景联系, figureFileSmall=uh0xWSG2YipG3gdEbjFGSQ==, figureFileBig=4rnmnJdvsDnp4QMjlrP0Bg==, tableContent=null), ArticleFig(id=1329458038802592092, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, label=Figure 6, caption=
Development of backdoor attack methods, figureFileSmall=Ttr18d/YpDf91JIEL4YwZA==, figureFileBig=YrsxaKFDh9xB+GUa1b1tIA==, tableContent=null), ArticleFig(id=1329458038970364253, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, label=图6, caption=
后门攻击方法的发展, figureFileSmall=Ttr18d/YpDf91JIEL4YwZA==, figureFileBig=YrsxaKFDh9xB+GUa1b1tIA==, tableContent=null), ArticleFig(id=1329458039087804766, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, label=Figure 7, caption=
Diagram of DBA changing global departure mode to local trigger mode, figureFileSmall=ujOn8IRZU/5IBMisZG7fOQ==, figureFileBig=EfMdk9NfVUqovrI9tEEUTQ==, tableContent=null), ArticleFig(id=1329458039154913631, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, label=图7, caption=
DBA将全局出发模式改为局部触发模式图, figureFileSmall=ujOn8IRZU/5IBMisZG7fOQ==, figureFileBig=EfMdk9NfVUqovrI9tEEUTQ==, tableContent=null), ArticleFig(id=1329458039205245280, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, label=Figure 8, caption=
Februus[18] reconstructs masked regions using GAN-based repair method, figureFileSmall=tinHmXvs4h5KBOJ1iLPwTQ==, figureFileBig=IQo22YhaYADYDkgGT9BTqQ==, tableContent=null), ArticleFig(id=1329458039314297185, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, label=图8, caption=
Februus[18]使用基于GAN的修复方法重建被屏蔽区域, figureFileSmall=tinHmXvs4h5KBOJ1iLPwTQ==, figureFileBig=IQo22YhaYADYDkgGT9BTqQ==, tableContent=null), ArticleFig(id=1329458039373017442, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, label=Table 1, caption=
Comparison of Our Paper with Other Federal Learning Review Literatures
, figureFileSmall=null, figureFileBig=null, tableContent=
| 文献 | 隐私问题 定义/分类 | 安全问题 定义/分类 | 攻击方法 分类/对比 | 防御方法 分类/对比 | 文献前沿 性/充分性 |
|---|
| 本文 | √√√ | √√ | √√√ | √√√ | √√√ |
| 文献[2] | √√ | √√√ | ◯ | ◯ | √ |
| 文献[3] | √ | √ | ◯ | ◯ | √ |
| 文献[4] | √√√ | √√√ | √ | √√√ | √ |
| 文献[5] | √√√ | √ | √ | √√ | √√√ |
), ArticleFig(id=1329458039435932003, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, label=表1, caption=
本文与其它联邦学习综述文献的对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 文献 | 隐私问题 定义/分类 | 安全问题 定义/分类 | 攻击方法 分类/对比 | 防御方法 分类/对比 | 文献前沿 性/充分性 |
|---|
| 本文 | √√√ | √√ | √√√ | √√√ | √√√ |
| 文献[2] | √√ | √√√ | ◯ | ◯ | √ |
| 文献[3] | √ | √ | ◯ | ◯ | √ |
| 文献[4] | √√√ | √√√ | √ | √√√ | √ |
| 文献[5] | √√√ | √ | √ | √√ | √√√ |
), ArticleFig(id=1329458039511429476, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, label=Table 2, caption=
Comparison of Backdoor Attacks with Adversarial Attacks and Data Poisoning
, figureFileSmall=null, figureFileBig=null, tableContent=
| 对比项目 | 攻击方式 |
|---|
| 后门攻击 | 对抗攻击 | 数据投毒 |
|---|
| 目的 | 嵌入触发器导致 模型错误预测 | 引入细微扰动 误导模型判断 | 注入错误信息 破坏模型性能 |
| 实施阶段 | 训练阶段 | 推理阶段 | 训练阶段 |
| 方法 | 在训练数据中嵌入特定模式或触发器 | 添加细微扰动 到输入数据 | 向训练数据中注入错误或误导性信息 |
| 影响 | 模型在特定条件下产生错误预测 | 模型做出错误判断 | 模型在广泛输入上表现不佳 |
| 特点 | 全局一致触发器,隐藏触发器 | 细微扰动, 实时攻击 | 异常样本,破坏 正常数据分布 |
), ArticleFig(id=1329458039599509861, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, label=表2, caption=
后门攻击与对抗攻击、数据投毒对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| 对比项目 | 攻击方式 |
|---|
| 后门攻击 | 对抗攻击 | 数据投毒 |
|---|
| 目的 | 嵌入触发器导致 模型错误预测 | 引入细微扰动 误导模型判断 | 注入错误信息 破坏模型性能 |
| 实施阶段 | 训练阶段 | 推理阶段 | 训练阶段 |
| 方法 | 在训练数据中嵌入特定模式或触发器 | 添加细微扰动 到输入数据 | 向训练数据中注入错误或误导性信息 |
| 影响 | 模型在特定条件下产生错误预测 | 模型做出错误判断 | 模型在广泛输入上表现不佳 |
| 特点 | 全局一致触发器,隐藏触发器 | 细微扰动, 实时攻击 | 异常样本,破坏 正常数据分布 |
), ArticleFig(id=1329458039670813030, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, label=Table 3, caption=
Summary of Backdoor Attack Scenario
, figureFileSmall=null, figureFileBig=null, tableContent=
| 攻击场景 | 攻击者角色 | 攻击者目的 | 攻击者能力 | | 攻击方式 |
|---|
训练 样本 | 标签 | 模型 | | 投毒 攻击 | 模型 攻击 |
|---|
| 外包 | 第三方服务商 | 将中毒模型 交付给用户 | √ | √ | ◯ | | √ | √ |
| 训练集供应商 | 训练集供应商 | 污染使用中毒数据集的用户 | √ | ◯ | ◯ | | √ | ◯ |
| 干净样本供应商 | 样本提供者 | 污染使用中毒样本的用户 | √ | √ | ◯ | | √ | √ |
| 模型训练 | 预测模型攻击者 | 污染使用预测模型的用户 | ◯ | √ | √ | | √ | √ |
| 模型迁移 | 模型迁移者 | 将后门嵌入 | √ | ◯ | √ | | √ | √ |
| 联邦学习 | 联邦学习恶意 参与者 | 将后门嵌入 全局服务器中 | √ | ◯ | √ | | √ | √ |
), ArticleFig(id=1329458039775670631, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, label=表3, caption=
后门攻击场景总结
, figureFileSmall=null, figureFileBig=null, tableContent=
| 攻击场景 | 攻击者角色 | 攻击者目的 | 攻击者能力 | | 攻击方式 |
|---|
训练 样本 | 标签 | 模型 | | 投毒 攻击 | 模型 攻击 |
|---|
| 外包 | 第三方服务商 | 将中毒模型 交付给用户 | √ | √ | ◯ | | √ | √ |
| 训练集供应商 | 训练集供应商 | 污染使用中毒数据集的用户 | √ | ◯ | ◯ | | √ | ◯ |
| 干净样本供应商 | 样本提供者 | 污染使用中毒样本的用户 | √ | √ | ◯ | | √ | √ |
| 模型训练 | 预测模型攻击者 | 污染使用预测模型的用户 | ◯ | √ | √ | | √ | √ |
| 模型迁移 | 模型迁移者 | 将后门嵌入 | √ | ◯ | √ | | √ | √ |
| 联邦学习 | 联邦学习恶意 参与者 | 将后门嵌入 全局服务器中 | √ | ◯ | √ | | √ | √ |
), ArticleFig(id=1329458039851168104, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, label=Table 4, caption=
Summary of Different Backdoor Attack Mechanisms Under Data Poisoning Classification
, figureFileSmall=null, figureFileBig=null, tableContent=
| 攻击方法 | 攻击类别 | 持续性 | 攻击机制 | 隐蔽性 | 成功率/ % |
|---|
| 标签翻转法 | 数据中毒 | √ | 产生有毒样本 | √ | |
| 干净标签法 | 数据中毒 | √ | 样本伪装 | √ | 76 |
| 可转移清洁标签法 | 数据中毒 | √ | 样本伪装 | √ | |
边缘数据下的 后门攻击 | 数据中毒 | √ | 长尾分布 | √ | 81 |
| 分布式后门攻击 | 数据中毒 | √ | 来自多个客户端的 嵌入式后门分布式 | √ | 83 |
| 动态后门攻击 | 数据中毒 | √ | 动态后门 | √ | |
| 变色龙[24] | 数据中毒 | √ | 自适应性技术 | √ | 95 |
), ArticleFig(id=1329458040023134569, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, label=表4, caption=
数据中毒分类下的不同后门攻击机制总结
, figureFileSmall=null, figureFileBig=null, tableContent=
| 攻击方法 | 攻击类别 | 持续性 | 攻击机制 | 隐蔽性 | 成功率/ % |
|---|
| 标签翻转法 | 数据中毒 | √ | 产生有毒样本 | √ | |
| 干净标签法 | 数据中毒 | √ | 样本伪装 | √ | 76 |
| 可转移清洁标签法 | 数据中毒 | √ | 样本伪装 | √ | |
边缘数据下的 后门攻击 | 数据中毒 | √ | 长尾分布 | √ | 81 |
| 分布式后门攻击 | 数据中毒 | √ | 来自多个客户端的 嵌入式后门分布式 | √ | 83 |
| 动态后门攻击 | 数据中毒 | √ | 动态后门 | √ | |
| 变色龙[24] | 数据中毒 | √ | 自适应性技术 | √ | 95 |
), ArticleFig(id=1329458040119603562, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, label=Table 5, caption=
Summary of Backdoor Attack Methods Under Federal Learning
, figureFileSmall=null, figureFileBig=null, tableContent=
攻击 方式 | 类型 | 来源 | 攻击者最小能力 | 触发器 可见性 |
|---|
| 样本 | 标签 | 模型 |
|---|
数据 中毒 | 简单型 | 文献[39] | ● | ● | ○ | 高 |
| 文献[40] | ● | ○ | ○ | 低 |
| 扰动型 | 文献[41] | ● | ● | ○ | 高 |
| 文献[42] | ● | ○ | ○ | 低 |
| 文献[43] | ● | ○ | ○ | 低 |
| 文献[28] | ● | ● | ○ | 低 |
| 文献[44] | ● | ○ | ○ | 低 |
| 缩放型 | 文献[45] | ● | ○ | ○ | 低 |
| 动态触发型 | 文献[46] | ● | ● | ○ | 低 |
| 文献[47] | ● | ● | ○ | 低 |
| 文献[48] | ● | ● | ○ | 低 |
| 特征碰撞型 | 文献[49] | ● | ○ | ● | 低 |
| 文献[50] | ● | ○ | ○ | 低 |
| 文献[30] | ● | ○ | ○ | 低 |
| 优化选择型 | 文献[51] | ● | ○ | ○ | 低 |
| 特征组合型 | 文献[52] | ● | ● | ○ | 低 |
模型 中毒 | 参数调整型 | 文献[53] | ○ | ○ | ● | 高 |
| 文献[54] | ○ | ○ | ● | 低 |
| 文献[55] | ○ | ○ | ● | 高 |
| 文献[56] | ○ | ○ | ● | 高 |
| 结构调整型 | 文献[57] | ○ | ○ | ● | 低 |
| 文献[58] | ○ | ○ | ● | 低 |
| 文献[59] | ● | ● | ● | 高 |
), ArticleFig(id=1329458040262209899, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, label=表5, caption=
联邦学习下的后门攻击方法总结
, figureFileSmall=null, figureFileBig=null, tableContent=
攻击 方式 | 类型 | 来源 | 攻击者最小能力 | 触发器 可见性 |
|---|
| 样本 | 标签 | 模型 |
|---|
数据 中毒 | 简单型 | 文献[39] | ● | ● | ○ | 高 |
| 文献[40] | ● | ○ | ○ | 低 |
| 扰动型 | 文献[41] | ● | ● | ○ | 高 |
| 文献[42] | ● | ○ | ○ | 低 |
| 文献[43] | ● | ○ | ○ | 低 |
| 文献[28] | ● | ● | ○ | 低 |
| 文献[44] | ● | ○ | ○ | 低 |
| 缩放型 | 文献[45] | ● | ○ | ○ | 低 |
| 动态触发型 | 文献[46] | ● | ● | ○ | 低 |
| 文献[47] | ● | ● | ○ | 低 |
| 文献[48] | ● | ● | ○ | 低 |
| 特征碰撞型 | 文献[49] | ● | ○ | ● | 低 |
| 文献[50] | ● | ○ | ○ | 低 |
| 文献[30] | ● | ○ | ○ | 低 |
| 优化选择型 | 文献[51] | ● | ○ | ○ | 低 |
| 特征组合型 | 文献[52] | ● | ● | ○ | 低 |
模型 中毒 | 参数调整型 | 文献[53] | ○ | ○ | ● | 高 |
| 文献[54] | ○ | ○ | ● | 低 |
| 文献[55] | ○ | ○ | ● | 高 |
| 文献[56] | ○ | ○ | ● | 高 |
| 结构调整型 | 文献[57] | ○ | ○ | ● | 低 |
| 文献[58] | ○ | ○ | ● | 低 |
| 文献[59] | ● | ● | ● | 高 |
), ArticleFig(id=1329458040337707373, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, label=Table 6, caption=
Summary of Different Backdoor Attack Mechanisms Under Model Poisoning Classification
, figureFileSmall=null, figureFileBig=null, tableContent=
| 攻击方法 | 攻击类别 | 持续性 | 攻击机制 | 隐蔽性 | 成功率/% |
|---|
| 语义后门攻击 | 模型中毒
| √ | 模型替换 | √ | 75 |
| 神经毒素法 | 模型中毒 | √ | 训练期间变化较小的攻击参数 | √ | 89 |
| 基于优化的后门攻击 | 模型中毒 | √ | 优化方法 | √ | 92 |
| 距离感知攻击 | 模型中毒 | √ | 攻击距离感知 | √ | 94 |
), ArticleFig(id=1329458040450953583, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, label=表6, caption=
模型中毒分类下的不同后门攻击机制总结
, figureFileSmall=null, figureFileBig=null, tableContent=
| 攻击方法 | 攻击类别 | 持续性 | 攻击机制 | 隐蔽性 | 成功率/% |
|---|
| 语义后门攻击 | 模型中毒
| √ | 模型替换 | √ | 75 |
| 神经毒素法 | 模型中毒 | √ | 训练期间变化较小的攻击参数 | √ | 89 |
| 基于优化的后门攻击 | 模型中毒 | √ | 优化方法 | √ | 92 |
| 距离感知攻击 | 模型中毒 | √ | 攻击距离感知 | √ | 94 |
), ArticleFig(id=1329458040518062448, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=EN, label=Table 7, caption=
Comparison of the Latest Methods for Defending Against Backdoor Attacks in Federate Learning
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 基于假设 | | 防御要求 |
|---|
| 防御目标 | 数据类型 | 模型中 毒率/% | | 访问 本地 | 访问 模型 |
|---|
| FLAME[58] | 后门攻击 | 非独立同分布 | < 50 | | √ | ◯ |
| DeepSight[31] | 后门攻击 | 非独立同分布 | ≤45 | | √ | √ |
| FoolsGold[25] | 分布式攻击 | 非独立同分布 | | | √ | ◯ |
| AUROR[27] | 分布式攻击 | 独立同分布 | ≤30 | | √ | ◯ |
| CAE[75] | 梯度替换 | | | | ◯ | ◯ |
| CRFL[76] | 分布式触发器 | 非独立同分布 | ≤4 | | √ | |
| BaFFle[77] | 分布式攻击 | 非独立同分布 | | | √ | √ |
| RLR[59] | 分布式触发器 | | 10 | | √ | ◯ |
| DP[78] | 单触发器 | 非独立同分布 | ≤5 | | √ | ◯ |
| FL-WBC[72] | 分布式攻击 | | ≤50 | | √ | ◯ |
), ArticleFig(id=1329458040589365617, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329458027746406655, language=CN, label=表7, caption=
联邦学习下防御后门攻击的最新方法比较
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 基于假设 | | 防御要求 |
|---|
| 防御目标 | 数据类型 | 模型中 毒率/% | | 访问 本地 | 访问 模型 |
|---|
| FLAME[58] | 后门攻击 | 非独立同分布 | < 50 | | √ | ◯ |
| DeepSight[31] | 后门攻击 | 非独立同分布 | ≤45 | | √ | √ |
| FoolsGold[25] | 分布式攻击 | 非独立同分布 | | | √ | ◯ |
| AUROR[27] | 分布式攻击 | 独立同分布 | ≤30 | | √ | ◯ |
| CAE[75] | 梯度替换 | | | | ◯ | ◯ |
| CRFL[76] | 分布式触发器 | 非独立同分布 | ≤4 | | √ | |
| BaFFle[77] | 分布式攻击 | 非独立同分布 | | | √ | √ |
| RLR[59] | 分布式触发器 | | 10 | | √ | ◯ |
| DP[78] | 单触发器 | 非独立同分布 | ≤5 | | √ | ◯ |
| FL-WBC[72] | 分布式攻击 | | ≤50 | | √ | ◯ |
)], 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/issn1000-1239.202440487, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202440487, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202440487, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202440487, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1727712000000, fullTextJson=null, articleText=null, reference=null)