Article(id=1327013201381798566, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327013054811845282, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202330826, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1697644800000, receivedDateStr=2023-10-19, revisedDate=1736697600000, revisedDateStr=2025-01-13, acceptedDate=1737820800000, acceptedDateStr=2025-01-26, onlineDate=1794314201922, onlineDateStr=2026-11-10, pubDate=1751299200000, pubDateStr=2025-07-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794314201922, onlineIssueDateStr=2026-11-10, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794314201922, creator=13701087609, updateTime=1794314201922, updator=13701087609, issue=Issue{id=1327013054811845282, tenantId=1146029695717560320, journalId=1324759914146529478, year='2025', volume='62', issue='7', pageStart='1595', pageEnd='1832', issueExtLink='null', onlineDate='null', pubDate='1751299200000', pubDateStr='2025-07-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794314166977, creator='13701087609', updateTime=1794376853183, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1327275980453950013, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327013054811845282, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1327275980453950014, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327013054811845282, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=1713, endPage=1737, ext={EN=ArticleExt(id=1327013201847366311, articleId=1327013201381798566, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Survey on Adversarial Attack and Defense for Signal Modulation Recognition, columnId=1325493671541474142, journalTitle=Journal of Computer Research and Development, columnName=Network and Information Security, runingTitle=null, highlight=null, articleAbstract=
With the rapid development of deep learning, signal modulation recognition based on deep neural networks has gained popularity in wireless communications research. However, it has been observed that the deep neural network model is vulnerable to adversarial perturbations, rendering the modulation identification task ineffective. Currently, there are theoretical gaps and bottlenecks in wireless communication security research. Due to the multidimensional nature of wireless communication, including factors such as experimental environments, data structures, and signal characteristics, it is not feasible to transfer the established attack and defense methods from other domains to signal countermeasures. In this paper, we comprehensively summarize the research on adversarial attack and defense technology in the field of signal modulation recognition. We propose a generic classification framework and threat model for adversarial attacks in this field. And we classify the research in this field into two categories: physical self-defense attacks and digital direct access attacks. Then, we systematically integrate and visualize the research as two-dimensional diagrams to demonstratively showcase the methods, models, and techniques of adversarial attack. Additionally, we provide details on the methods and models of adversarial attack. We present the existing research on adversarial attack methods, adversarial examples generation techniques, theoretical formulas, and adversarial detection and defense techniques. We systematically refine the characteristics of the three dimensions of adversarial attacks on wireless communications and summarize the corresponding processing methods. Finally, we summarize the future research and development direction of the attack and defense security field oriented towards signal modulation recognition.
, authors=Dongyue Xu
1, Yunzhe Tian
1, Kang Chen
1, Yike Li
1, Yalun Wu
1, Endong Tong
1, Wenjia Niu
1, *, Jiqiang Liu
1, Zhongzhi Shi
2, authorsList=Dongyue Xu, Yunzhe Tian, Kang Chen, Yike Li, Yalun Wu, Endong Tong, Wenjia Niu, Jiqiang Liu, Zhongzhi Shi, authorCompany=null, correspAuthors=Wenjia Niu, authorNote=
born in 1999. Master. Her main research interest includes adversarial machine learning
born in 1999. PhD candidate. His main research interest includes AI security
born in 1999. Master. His main research interest includes signal modulation recognition
born in 1995. PhD. Her main research interest includes AI security
born in 1994. PhD candidate. His main research interest includes AI security
born in 1986. PhD, lecturer. Member of CCF. His main research interests include AI security, services computing, and data mining
born in 1982. PhD, professor, PhD supervisor. Distinguished member of CCF. His main research interests include AI security and data mining
born in 1973. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include trusted computing, cryptographic protocols, privacy preserving, and network security
born in 1941. Professor, PhD supervisor. Fellow of CCF. His main research interests include artificial intelligence, machine learning, and neural computing and cognitive science
, correspAuthorsNote=null, copyrightStatement=Copyright © 2025 Journal of Computer Research and Development. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1327013209124483786, articleId=1327013201381798566, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=面向信号调制识别的对抗攻击与防御综述, columnId=1325493672690713440, journalTitle=计算机研究与发展, columnName=网络与信息安全, runingTitle=null, highlight=null, articleAbstract=
随着深度学习的飞速发展,基于深度神经网络的信号调制识别任务成为无线通信领域热门研究. 研究发现,深度神经网络模型极易受到对抗性扰动的影响,使调制识别任务失效. 目前面向无线通信安全性的研究工作仍存在些许瓶颈问题与理论空白,源于无线通信固有的实验环境、数据结构与信号特征等多维度特性,不能将其他领域较为成熟的攻防方法简单迁移到信号对抗攻击中. 面向信号调制识别领域的对抗攻防,总结该领域对抗攻击与防御技术研究工作,提出信号调制识别领域的通用对抗攻击分类框架与威胁模型,将该领域研究工作分类为物理自我防御式攻击和数字直接访问式攻击,并以2维图形式进行系统化整合与可视化展示,详细阐述对抗攻击方法、对抗样本生成技术与理论公式、对抗检测与防御技术最新的研究工作,系统提炼无线通信对抗攻击研究的3个维度特性并归纳相应的处理方法,最后总结面向信号调制识别的攻防安全领域在未来的研究发展方向.
, authors=徐冬月
1, 田蕴哲
1, 陈康
1, 李轶珂
1, 吴亚伦
1, 童恩栋
1, 牛温佳
1, *, 刘吉强
1, 史忠植
2, authorsList=徐冬月, 田蕴哲, 陈康, 李轶珂, 吴亚伦, 童恩栋, 牛温佳, 刘吉强, 史忠植, authorCompany=null, correspAuthors=牛温佳, authorNote=
 |
1999年生. 硕士. 主要研究方向为对抗机器学习 |
 |
1999年生. 博士研究生. 主要研究方向为人工智能安全 |
 |
1999年生. 硕士. 主要研究方向为信号调制识别 |
 |
1995年生. 博士. 主要研究方向为人工智能安全 |
 |
1994年生. 博士研究生. 主要研究方向为人工智能安全 |
 |
1986年生. 博士,讲师. CCF会员. 主要研究方向为人工智能安全、服务计算、数据挖掘 |
 |
1982年生. 博士,教授,博士生导师. CCF杰出会员. 主要研究方向为人工智能安全、数据挖掘 |
 |
1973年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为可信计算、加密协议、隐私保护、网络安全 |
 |
1941年生. 教授,博士生导师. CCF会士. 主要研究方向为人工智能、机器学习、神经计算与认知科学 |
, correspAuthorsNote=
, copyrightStatement=版权所有 © 2025 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=EfXns0lX/kiUbgcMokSnRw==, magXml=lIki4QrkWTGk1uWtOs6+NQ==, pdfUrl=null, pdf=PD3P6h49MjbpYbBpbUqA3A==, pdfFileSize=2398565, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=uZuRLJsLjmpg2hfJ0sWojQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=qhE0vglGC/q0Yu3IBTrbdg==, mapNumber=null, fund=null)}, authors=[Author(id=1327013209766212306, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=dongyuexu@bjtu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327013209862681300, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013209766212306, language=EN, stringName=Dongyue Xu, firstName=Dongyue, middleName=null, lastName=Xu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100044, bio={"content":"
born in 1999. Master. Her main research interest includes adversarial machine learning
"}, bioImg=null, bioContent=
born in 1999. Master. Her main research interest includes adversarial machine learning
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013209946567381, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013209766212306, language=CN, stringName=徐冬月, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1智能交通数据安全与隐私保护北京市重点实验室(北京交通大学) 北京 100044, bio={"img":"1Nz/bdyYxsLlxb79gfzhwQ==","content":"
1999年生. 硕士. 主要研究方向为对抗机器学习
"}, bioImg=1Nz/bdyYxsLlxb79gfzhwQ==, bioContent=
1999年生. 硕士. 主要研究方向为对抗机器学习
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013209531331275, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, xref=1, ext=[AuthorCompanyExt(id=1327013209564885708, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100044), AuthorCompanyExt(id=1327013209577468621, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1智能交通数据安全与隐私保护北京市重点实验室(北京交通大学) 北京 100044)])]), Author(id=1327013210043036375, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327013210160476889, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013210043036375, language=EN, stringName=Yunzhe Tian, firstName=Yunzhe, middleName=null, lastName=Tian, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100044, bio={"content":"
born in 1999. PhD candidate. His main research interest includes AI security
"}, bioImg=null, bioContent=
born in 1999. PhD candidate. His main research interest includes AI security
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013210290500315, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013210043036375, language=CN, stringName=田蕴哲, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1智能交通数据安全与隐私保护北京市重点实验室(北京交通大学) 北京 100044, bio={"img":"Xqp0GBNoN+qbNy3QKhMA/w==","content":"
1999年生. 博士研究生. 主要研究方向为人工智能安全
"}, bioImg=Xqp0GBNoN+qbNy3QKhMA/w==, bioContent=
1999年生. 博士研究生. 主要研究方向为人工智能安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013209531331275, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, xref=1, ext=[AuthorCompanyExt(id=1327013209564885708, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100044), AuthorCompanyExt(id=1327013209577468621, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1智能交通数据安全与隐私保护北京市重点实验室(北京交通大学) 北京 100044)])]), Author(id=1327013210403746525, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, 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=1327013210496021215, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013210403746525, language=EN, stringName=Kang Chen, firstName=Kang, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100044, bio={"content":"
born in 1999. Master. His main research interest includes signal modulation recognition
"}, bioImg=null, bioContent=
born in 1999. Master. His main research interest includes signal modulation recognition
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013210605073120, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013210403746525, language=CN, stringName=陈康, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1智能交通数据安全与隐私保护北京市重点实验室(北京交通大学) 北京 100044, bio={"img":"3a3ESfTt3E9SWM7BNfrHxA==","content":"
1999年生. 硕士. 主要研究方向为信号调制识别
"}, bioImg=3a3ESfTt3E9SWM7BNfrHxA==, bioContent=
1999年生. 硕士. 主要研究方向为信号调制识别
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013209531331275, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, xref=1, ext=[AuthorCompanyExt(id=1327013209564885708, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100044), AuthorCompanyExt(id=1327013209577468621, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1智能交通数据安全与隐私保护北京市重点实验室(北京交通大学) 北京 100044)])]), Author(id=1327013212291183330, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, 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=1327013212412818149, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013212291183330, language=EN, stringName=Yike Li, firstName=Yike, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100044, bio={"content":"
born in 1995. PhD. Her main research interest includes AI security
"}, bioImg=null, bioContent=
born in 1995. PhD. Her main research interest includes AI security
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013212496704230, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013212291183330, language=CN, stringName=李轶珂, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1智能交通数据安全与隐私保护北京市重点实验室(北京交通大学) 北京 100044, bio={"img":"1ExCu21MkyjOalBzwpKS7g==","content":"
1995年生. 博士. 主要研究方向为人工智能安全
"}, bioImg=1ExCu21MkyjOalBzwpKS7g==, bioContent=
1995年生. 博士. 主要研究方向为人工智能安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013209531331275, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, xref=1, ext=[AuthorCompanyExt(id=1327013209564885708, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100044), AuthorCompanyExt(id=1327013209577468621, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1智能交通数据安全与隐私保护北京市重点实验室(北京交通大学) 北京 100044)])]), Author(id=1327013212576396008, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, 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=1327013212656087786, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013212576396008, language=EN, stringName=Yalun Wu, firstName=Yalun, middleName=null, lastName=Wu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100044, bio={"content":"
born in 1994. PhD candidate. His main research interest includes AI security
"}, bioImg=null, bioContent=
born in 1994. PhD candidate. His main research interest includes AI security
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013212748362475, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013212576396008, language=CN, stringName=吴亚伦, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1智能交通数据安全与隐私保护北京市重点实验室(北京交通大学) 北京 100044, bio={"img":"3wBG2kvGhfKngY2tRZ9XDA==","content":"
1994年生. 博士研究生. 主要研究方向为人工智能安全
"}, bioImg=3wBG2kvGhfKngY2tRZ9XDA==, bioContent=
1994年生. 博士研究生. 主要研究方向为人工智能安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013209531331275, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, xref=1, ext=[AuthorCompanyExt(id=1327013209564885708, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100044), AuthorCompanyExt(id=1327013209577468621, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1智能交通数据安全与隐私保护北京市重点实验室(北京交通大学) 北京 100044)])]), Author(id=1327013212828054253, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=edtong@bjtu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327013212932911855, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013212828054253, language=EN, stringName=Endong Tong, firstName=Endong, middleName=null, lastName=Tong, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100044, bio={"content":"
born in 1986. PhD, lecturer. Member of CCF. His main research interests include AI security, services computing, and data mining
"}, bioImg=null, bioContent=
born in 1986. PhD, lecturer. Member of CCF. His main research interests include AI security, services computing, and data mining
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013213029380848, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013212828054253, language=CN, stringName=童恩栋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1智能交通数据安全与隐私保护北京市重点实验室(北京交通大学) 北京 100044, bio={"img":"fFwMe6+cjkHoiuhyCTJAPg==","content":"
1986年生. 博士,讲师. CCF会员. 主要研究方向为人工智能安全、服务计算、数据挖掘
"}, bioImg=fFwMe6+cjkHoiuhyCTJAPg==, bioContent=
1986年生. 博士,讲师. CCF会员. 主要研究方向为人工智能安全、服务计算、数据挖掘
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013209531331275, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, xref=1, ext=[AuthorCompanyExt(id=1327013209564885708, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100044), AuthorCompanyExt(id=1327013209577468621, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1智能交通数据安全与隐私保护北京市重点实验室(北京交通大学) 北京 100044)])]), Author(id=1327013213151015666, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=niuwj@bjtu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1327013213247484660, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013213151015666, language=EN, stringName=Wenjia Niu, firstName=Wenjia, middleName=null, lastName=Niu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, *, address=
1Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100044, bio={"content":"
born in 1982. PhD, professor, PhD supervisor. Distinguished member of CCF. His main research interests include AI security and data mining
"}, bioImg=null, bioContent=
born in 1982. PhD, professor, PhD supervisor. Distinguished member of CCF. His main research interests include AI security and data mining
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013213327176437, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013213151015666, language=CN, stringName=牛温佳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, *, address=
1智能交通数据安全与隐私保护北京市重点实验室(北京交通大学) 北京 100044, bio={"img":"v2thGn1if/tm5H3nXaITvw==","content":"
1982年生. 博士,教授,博士生导师. CCF杰出会员. 主要研究方向为人工智能安全、数据挖掘
"}, bioImg=v2thGn1if/tm5H3nXaITvw==, bioContent=
1982年生. 博士,教授,博士生导师. CCF杰出会员. 主要研究方向为人工智能安全、数据挖掘
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013209531331275, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, xref=1, ext=[AuthorCompanyExt(id=1327013209564885708, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100044), AuthorCompanyExt(id=1327013209577468621, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1智能交通数据安全与隐私保护北京市重点实验室(北京交通大学) 北京 100044)])]), Author(id=1327013213432034039, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, orderNo=7, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327013213524308729, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013213432034039, language=EN, stringName=Jiqiang Liu, firstName=Jiqiang, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100044, bio={"content":"
born in 1973. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include trusted computing, cryptographic protocols, privacy preserving, and network security
"}, bioImg=null, bioContent=
born in 1973. PhD, professor, PhD supervisor. Senior member of CCF. His main research interests include trusted computing, cryptographic protocols, privacy preserving, and network security
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013213616583418, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013213432034039, language=CN, stringName=刘吉强, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
1, address=
1智能交通数据安全与隐私保护北京市重点实验室(北京交通大学) 北京 100044, bio={"img":"Bomqp2BN0Crw7l7LsfOLLw==","content":"
1973年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为可信计算、加密协议、隐私保护、网络安全
"}, bioImg=Bomqp2BN0Crw7l7LsfOLLw==, bioContent=
1973年生. 博士,教授,博士生导师. CCF高级会员. 主要研究方向为可信计算、加密协议、隐私保护、网络安全
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013209531331275, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, xref=1, ext=[AuthorCompanyExt(id=1327013209564885708, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100044), AuthorCompanyExt(id=1327013209577468621, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1智能交通数据安全与隐私保护北京市重点实验室(北京交通大学) 北京 100044)])]), Author(id=1327013213725635324, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, orderNo=8, 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=1327013213864047358, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013213725635324, language=EN, stringName=Zhongzhi Shi, firstName=Zhongzhi, middleName=null, lastName=Shi, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, bio={"content":"
born in 1941. Professor, PhD supervisor. Fellow of CCF. His main research interests include artificial intelligence, machine learning, and neural computing and cognitive science
"}, bioImg=null, bioContent=
born in 1941. Professor, PhD supervisor. Fellow of CCF. His main research interests include artificial intelligence, machine learning, and neural computing and cognitive science
, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013213960516351, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, authorId=1327013213725635324, language=CN, stringName=史忠植, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
2, address=
2中国科学院计算技术研究所智能信息处理重点实验室 北京 100190, bio={"img":"4po/cONF5y9BCfhfyzHtkA==","content":"
1941年生. 教授,博士生导师. CCF会士. 主要研究方向为人工智能、机器学习、神经计算与认知科学
"}, bioImg=4po/cONF5y9BCfhfyzHtkA==, bioContent=
1941年生. 教授,博士生导师. CCF会士. 主要研究方向为人工智能、机器学习、神经计算与认知科学
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013209669743310, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, xref=2, ext=[AuthorCompanyExt(id=1327013209682326223, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209669743310, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190), AuthorCompanyExt(id=1327013209690714832, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209669743310, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院计算技术研究所智能信息处理重点实验室 北京 100190)])])], keywords=[Keyword(id=1327013214069568256, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, orderNo=1, keyword=deep neural network), Keyword(id=1327013214161842945, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, orderNo=2, keyword=wireless communication), Keyword(id=1327013214237340418, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, orderNo=3, keyword=signal modulation recognition), Keyword(id=1327013214346392323, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, orderNo=4, keyword=adversarial attack), Keyword(id=1327013214442861316, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, orderNo=5, keyword=defense), Keyword(id=1327013214514164485, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, orderNo=1, keyword=深度神经网络), Keyword(id=1327013214719685383, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, orderNo=2, keyword=无线通信), Keyword(id=1327013214862291720, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, orderNo=3, keyword=信号调制识别), Keyword(id=1327013214967149322, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, orderNo=4, keyword=对抗攻击), Keyword(id=1327013215092978443, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, orderNo=5, keyword=防御)], refs=[Reference(id=1327013226274992948, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, 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=Bhatti F A, Khan M J, Selim A, et al. Shared spectrum monitoring using deep learning[J]. IEEE Transactions on Cognitive Communications and Networking, 2021, 7(4): 1171−1185, articleTitle=null, refAbstract=null), Reference(id=1327013226354684725, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, 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=Dobre O A, Abdi A, Bar-Ness Y, et al. Survey of automatic modulation classification techniques: Classical approaches and new trends[J]. IET Communications, 2007, 1(2): 137−156, articleTitle=null, refAbstract=null), Reference(id=1327013226425987894, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Wenhan, Feng Mingjie, Krunz M, et al. Signal detection and classification in shared spectrum: A deep learning approach[C/OL]//Proc of the 40th IEEE Conf on Computer Communications. Piscataway, NJ: IEEE, 2021[2023-02-02]. https://ieeexplore.ieee.org/abstract/document/9488834/, articleTitle=null, refAbstract=null), Reference(id=1327013226497291063, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=O’Shea T J, Corgan J, Clancy T C. Convolutional radio modulation recognition networks[C]//Proc of the 17th Int Conf on Engineering Applications of Neural Networks. Cham: Springer, 2016: 213−226, articleTitle=null, refAbstract=null), Reference(id=1327013226572788536, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=West N E, O’Shea T. Deep architectures for modulation recognition[C/OL]//Proc of the 2017 IEEE Int Symp on Dynamic Spectrum Access Networks. Piscataway, NJ: IEEE, 2017[2023-02-02]. https://ieeexplore.ieee.org/abstract/document/7920754/, articleTitle=null, refAbstract=null), Reference(id=1327013226644091705, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Hong Dehua, Zhang Zilong, Xu Xiaodong. Automatic modulation classification using recurrent neural networks[C]//Proc of the 3rd IEEE Int Conf on Computer and Communications. Piscataway, NJ: IEEE, 2017: 695−700, articleTitle=null, refAbstract=null), Reference(id=1327013226715394874, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=Rajendran S, Meert W, Giustiniano D, et al. Deep learning models for wireless signal classification with distributed low-cost spectrum sensors[J]. IEEE Transactions on Cognitive Communications and Networking, 2018, 4(3): 433−445, articleTitle=null, refAbstract=null), Reference(id=1327013226786698043, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Hu Shisheng, Pei Yiyang, Liang P P, et al. Deep neural network for robust modulation classification under uncertain noise conditions[J]. IEEE Transactions on Vehicular Technology, 2020, 69(1): 564−577, articleTitle=null, refAbstract=null), Reference(id=1327013226874778428, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Jialang, Luo Chunbo, Parr G, et al. A spatiotemporal multi-channel learning framework for automatic modulation recognition[J]. IEEE Wireless Communications Letters, 2020, 9(10): 1629−1632, articleTitle=null, refAbstract=null), Reference(id=1327013226975441725, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Huynh-The T, Hua C H, Pham Q V, et al. MCNet: An efficient CNN architecture for robust automatic modulation classification[J]. IEEE Communications Letters, 2020, 24(4): 811−815, articleTitle=null, refAbstract=null), Reference(id=1327013227059327806, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Fuxin, Luo Chunbo, Xu Jialang, et al. An efficient deep learning model for automatic modulation recognition based on parameter estimation and transformation[J]. IEEE Communications Letters, 2021, 25(10): 3287−3290, articleTitle=null, refAbstract=null), Reference(id=1327013227151602495, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Shi Fengyuan, Hu Zeming, Yue Chunsheng, et al. Combining neural networks for modulation recognition[J]. Digital Signal Processing, 2022, 120: 103264, articleTitle=null, refAbstract=null), Reference(id=1327013227239682880, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Szegedy C, Zaremba W, Sutskever I, et al. Intriguing properties of neural networks[J]. arXiv preprint, arXiv: 1312.6199, 2013, articleTitle=null, refAbstract=null), Reference(id=1327013227315180353, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Goodfellow I J, Shlens J, Szegedy C. Explaining and harnessing adversarial examples[J]. arXiv preprint, arXiv: 1412.6572, 2015, articleTitle=null, refAbstract=null), Reference(id=1327013227386483522, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Kim B, Sagduyu Y E, Davaslioglu K, et al. Channel-aware adversarial attacks against deep learning-based wireless signal classifiers[J]. IEEE Transactions on Wireless Communications, 2022, 21(6): 3868−3880, articleTitle=null, refAbstract=null), Reference(id=1327013227466175299, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Sadeghi M, Larsson E G. Adversarial attacks on deep-learning based radio signal classification[J]. IEEE Wireless Communications Letters, 2019, 8(1): 213−216, articleTitle=null, refAbstract=null), Reference(id=1327013227541672772, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Tu Ya, Lin Yun, Wang Jin, et al. Semi-supervised learning with generative adversarial networks on digital signal modulation classification[J]. Computers, Materials & Continua, 2018, 55(2): 243−254, articleTitle=null, refAbstract=null), Reference(id=1327013227629753157, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Haojun, Lin Yun, Gao Song, et al. Evaluating and improving adversarial attacks on DNN-based modulation recognition[C/OL]//Proc of the 63rd IEEE Global Communications Conf. Piscataway, NJ: IEEE, 2020[2023-02-02]. https://ieeexplore.ieee.org/abstract/document/9322088/, articleTitle=null, refAbstract=null), Reference(id=1327013227705250630, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Flowers B, Buehrer R M, Headley W C. Evaluating adversarial evasion attacks in the context of wireless communications[J]. IEEE Transactions on Information Forensics and Security, 2020, 15: 1102−1113, articleTitle=null, refAbstract=null), Reference(id=1327013227805913927, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Yun, Zhao Haojun, Ma Xuefei, et al. Adversarial attacks in modulation recognition with convolutional neural networks[J]. IEEE Transactions on Reliability, 2021, 70(1): 389−401, articleTitle=null, refAbstract=null), Reference(id=1327013227906577224, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Tu Ya, Lin Yun, Zha Haoran, et al. Large-scale real-world radio signal recognition with deep learning[J]. Chinese Journal of Aeronautics, 2022, 35(9): 35−48, articleTitle=null, refAbstract=null), Reference(id=1327013228036600649, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Bao Zhida, Lin Yun, Zhang Sicheng, et al. Threat of adversarial attacks on DL-based IoT device identification[J]. IEEE Internet of Things Journal, 2022, 9(11): 9012−9024, articleTitle=null, refAbstract=null), Reference(id=1327013228145652554, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Sicheng, Lin Yun, Bao Zhida, et al. A lightweight modulation classification network resisting white box gradient attacks[J]. Security and Communication Networks, 2021(1): 8921485, articleTitle=null, refAbstract=null), Reference(id=1327013228246315851, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Hou Changbo, Liu Guowei, Tian Qiao, et al. Multisignal modulation classification using sliding window detection and complex convolutional network in frequency domain[J]. IEEE Internet of Things Journal, 2022, 9(19): 19438−19449, articleTitle=null, refAbstract=null), Reference(id=1327013228326007628, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Bahramali A, Nasr M, Houmansadr A, et al. Robust adversarial attacks against DNN-based wireless communication systems[C]//Proc of the 28th ACM SIGSAC Conf on Computer and Communications Security(CCS’21). New York: ACM, 2021: 126−140, articleTitle=null, refAbstract=null), Reference(id=1327013228405699405, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Kokalj-Filipovic S, Miller R, Chang N, et al. Mitigation of adversarial examples in RF deep classifiers utilizing autoencoder pre-training[C/OL]//Proc of the 2019 Int Conf on Military Communications and Information Systems. Piscataway, NJ: IEEE, 2019[2023-02-02]. https://ieeexplore.ieee.org/abstract/document/8842663/, articleTitle=null, refAbstract=null), Reference(id=1327013228489585486, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Kokalj-Filipovic S, Miller R, Vanhoy G. Adversarial examples in RF deep learning: Detection and physical robustness[C/OL]//Proc of the 2019 IEEE Global Conf on Signal and Information Processing. Piscataway, NJ: IEEE, 2019[2023-02-02]. https://ieeexplore.ieee.org/abstract/document/8969138/, articleTitle=null, refAbstract=null), Reference(id=1327013228598637391, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Adesina D, Hsieh C C, Sagduyu Y E, et al. Adversarial machine learning in wireless communications using RF data: A review[J]. IEEE Communications Surveys & Tutorials, 2022, 25(1): 77−100, articleTitle=null, refAbstract=null), Reference(id=1327013230263776080, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Flowers B, Buehrer R M, Headley W C. Communications aware adversarial residual networks for over the air evasion attacks[C]//Proc of the 2019 IEEE Military Communications Conf. Piscataway, NJ: IEEE, 2019: 133−140, articleTitle=null, refAbstract=null), Reference(id=1327013230372827985, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Huynh-The T, Pham Q V, Nguyen T V, et al. Automatic modulation classification: A deep architecture survey[J]. IEEE Access, 2021, 9: 142950−142971, articleTitle=null, refAbstract=null), Reference(id=1327013230477685586, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=O’Shea T, Hoydis J. An introduction to deep learning for the physical layer[J]. IEEE Transactions on Cognitive Communications and Networking, 2017, 3(4): 563−575, articleTitle=null, refAbstract=null), Reference(id=1327013230565765971, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Erpek T, O’Shea T J, Sagduyu Y E, et al. Deep learning for wireless communications[J]. Development and Analysis of Deep Learning Architectures, 2020, 867: 223−266, articleTitle=null, refAbstract=null), Reference(id=1327013230649652052, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Peng Shengliang, Sun Shujun, Yao Y D. A survey of modulation classification using deep learning: Signal representation and data preprocessing[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(12): 7020−7038, articleTitle=null, refAbstract=null), Reference(id=1327013230733538133, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Ruolin, Liu Fugang, Gravelle C W. Deep learning for modulation recognition: A survey with a demonstration[J]. IEEE Access, 2020, 8: 67366−67376, articleTitle=null, refAbstract=null), Reference(id=1327013230809035606, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Kingma D P, Ba J. Adam: A method for stochastic optimization[J]. arXiv preprint, arXiv: 1412.6980, 2014, articleTitle=null, refAbstract=null), Reference(id=1327013230913893208, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=O’Shea T J, Roy T, Clancy T C. Over-the-air deep learning based radio signal classification[J]. IEEE Journal of Selected Topics in Signal Processing, 2018, 12(1): 168−179, articleTitle=null, refAbstract=null), Reference(id=1327013231207494489, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Blossom E. GNU Radio: Tools for exploring the radio frequency spectrum[J/OL]. Linux Journal, 2004[2023-02-02]. https://dl.acm.org/doi/fullHtml/10.5555/993247.993251, articleTitle=null, refAbstract=null), Reference(id=1327013231341712218, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Tekbiyik K, Ekti A R, Gorcin A, et al. Robust and fast automatic modulation classification with CNN under multipath fading channels[C/OL]//Proc of the 91st IEEE Vehicular Technology Conf. Piscataway, NJ: IEEE, 2020[2023-02-02]. https://ieeexplore.ieee.org/abstract/document/9128408/, articleTitle=null, refAbstract=null), Reference(id=1327013231509484379, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Mendis G J, Wei-Kocsis J, Madanayake A. Deep learning based radio-signal identification with hardware design[J]. IEEE Transactions on Aerospace and Electronic Systems, 2019, 55(5): 2516−2531, articleTitle=null, refAbstract=null), Reference(id=1327013235045282652, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee J, Kim B, Kim J, et al. Deep neural network-based blind modulation classification for fading channels[C]//Proc of the 8th Int Conf on Information and Communication Technology Convergence. Piscataway, NJ: IEEE, 2017: 551−554, articleTitle=null, refAbstract=null), Reference(id=1327013235192083294, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Xiaoyu, Yang Diyu, Gamal A E. Deep neural network architectures for modulation classification[C]//Proc of the 51st Asilomar Conf on Signals, Systems, and Computers. Piscataway, NJ: IEEE, 2017: 915−919, articleTitle=null, refAbstract=null), Reference(id=1327013235292746592, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Mendis G J, Wei Jin, Madanayake A. Deep learning-based automated modulation classification for cognitive radio[C/OL]//Proc of the 2016 IEEE Int Conf on Communication Systems. Piscataway, NJ: IEEE, 2016[2023-02-02]. https://ieeexplore.ieee.org/abstract/document/7833571/, articleTitle=null, refAbstract=null), Reference(id=1327013235397604193, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Ali A, Yangyu F.
k-sparse autoencoder-based automatic modulation classification with low complexity[J]. IEEE Communications Letters, 2017, 21(10): 2162−2165, articleTitle=null, refAbstract=null), Reference(id=1327013235494073186, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Dai Ao, Zhang Haijian, Sun Hong. Automatic modulation classification using stacked sparse auto-encoders[C]//Proc of the 2016 IEEE Int Conf on Signal Processing. Piscataway, NJ: IEEE, 2016: 248−252, articleTitle=null, refAbstract=null), Reference(id=1327013235598930787, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Xie Wenwu, Hu Sheng, Yu Chao, et al. Deep learning in digital modulation recognition using high order cumulants[J]. IEEE Access, 2019, 7: 63760−63766, articleTitle=null, refAbstract=null), Reference(id=1327013235728954212, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Shi Wenzhe, Liu Dejun, Cheng Xing, et al. Particle swarm optimization-based deep neural network for digital modulation recognition[J]. IEEE Access, 2019, 7: 104591−104600, articleTitle=null, refAbstract=null), Reference(id=1327013235829617509, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Yashashwi K, Sethi A, Chaporkar P. A learnable distortion correction module for modulation recognition[J]. IEEE Wireless Communications Letters, 2019, 8(1): 77−80, articleTitle=null, refAbstract=null), Reference(id=1327013235930280806, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Zeng Yuan, Zhang Meng, Han Fei, et al. Spectrum analysis and convolutional neural network for automatic modulation recognition[J]. IEEE Wireless Communications Letters, 2019, 8(3): 929−932, articleTitle=null, refAbstract=null), Reference(id=1327013236047721319, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Peng Shengliang, Jiang Hanyu, Wang Huaxia, et al. Modulation classification based on signal constellation diagrams and deep learning[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30(3): 718−727, articleTitle=null, refAbstract=null), Reference(id=1327013236123218792, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Zufan, Wang Chun, Gan Chenquan, et al. Automatic modulation classification using convolutional neural network with features fusion of SPWVD and BJD[J]. IEEE Transactions on Signal and Information Processing over Networks, 2019, 5(3): 469−478, articleTitle=null, refAbstract=null), Reference(id=1327013236211299177, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Hao, Li Yaxing, Zhou Liang, et al. Convolutional neural network and multi‐feature fusion for automatic modulation classification[J]. Electronics Letters, 2019, 55(16): 895−897, articleTitle=null, refAbstract=null), Reference(id=1327013236324545386, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Yu, Liu Miao, Yang Jie, et al. Data-driven deep learning for automatic modulation recognition in cognitive radios[J]. IEEE Transactions on Vehicular Technology, 2019, 68(4): 4074−4077, articleTitle=null, refAbstract=null), Reference(id=1327013236416820075, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Danshi, Zhang Min, Li Ze, et al. Modulation format recognition and OSNR estimation using CNN-based deep learning[J]. IEEE Photonics Technology Letters, 2017, 29(19): 1667−1670, articleTitle=null, refAbstract=null), Reference(id=1327013236513289068, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee J H, Kim K Y, Shin Y. Feature image-based automatic modulation classification method using CNN algorithm[C/OL]//Proc of the 2019 Int Conf on Artificial Intelligence in Information and Communication. Piscataway, NJ: IEEE, 2019[2023-02-02]. https://ieeexplore.iee e.org/abstract/document/8669002/, articleTitle=null, refAbstract=null), Reference(id=1327013236676866925, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=55, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Zhuangzhi, Cui Hui, Xiang Jingyang, et al. SigNet: A novel deep learning framework for radio signal classification[J]. IEEE Transactions on Cognitive Communications and Networking, 2021, 8(2): 529−541, articleTitle=null, refAbstract=null), Reference(id=1327013236806890350, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=56, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=Hermawan A P, Ginanjar R R, Kim D S, et al. CNN-based automatic modulation classification for beyond 5G communications[J]. IEEE Communications Letters, 2020, 24(5): 1038−1041, articleTitle=null, refAbstract=null), Reference(id=1327013236911747951, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=57, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Ke Ziqi, Vikalo H. Real-time radio technology and modulation classification via an LSTM auto-encoder[J]. IEEE Transactions on Wireless Communications, 2022, 21(1): 370−382, articleTitle=null, refAbstract=null), Reference(id=1327013237033382768, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=58, rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=Chang Shuo, Huang Sai, Zhang Ruiyun, et al. Multitask-learning-based deep neural network for automatic modulation classification[J]. IEEE Internet of Things Journal, 2022, 9(3): 2192−2206, articleTitle=null, refAbstract=null), Reference(id=1327013237155017585, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=59, rfOrder=58, authorNames=null, journalName=null, refType=null, unstructuredReference=Ghasemzadeh P, Banerjee S, Hempel M, et al. A novel deep learning and polar transformation framework for an adaptive automatic modulation classification[J]. IEEE Transactions on Vehicular Technology, 2020, 69(11): 13243−13258, articleTitle=null, refAbstract=null), Reference(id=1327013237243097970, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=60, rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=Akhtar N, Mian A. Threat of adversarial attacks on deep learning in computer vision: A survey[J]. IEEE Access, 2018, 6: 14410−14430, articleTitle=null, refAbstract=null), Reference(id=1327013240787284852, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=61, rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=Cao Yangjie, Jia Lili, Chen Yongxia, et al. Recent advances of generative adversarial networks in computer vision[J]. IEEE Access, 2019, 7: 14985−15006, articleTitle=null, refAbstract=null), Reference(id=1327013240942474101, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=62, rfOrder=61, authorNames=null, journalName=null, refType=null, unstructuredReference=Akhtar N, Mian A, Kardan N, et al. Advances in adversarial attacks and defenses in computer vision: A survey[J]. IEEE Access, 2021, 9: 155161−155196, articleTitle=null, refAbstract=null), Reference(id=1327013241055720310, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=63, rfOrder=62, authorNames=null, journalName=null, refType=null, unstructuredReference=Zou Zhengxia, Lei Sen, Shi Tianyang, et al. Deep adversarial decomposition: A unified framework for separating superimposed images[C]//Proc of the 2020 IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2020: 12803−12813, articleTitle=null, refAbstract=null), Reference(id=1327013241252852599, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=64, rfOrder=63, authorNames=null, journalName=null, refType=null, unstructuredReference=Sarafianos N, Xu Xiang, Kakadiaris I. Adversarial representation learning for text-to-image matching[C]//Proc of the 2019 IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 5814−5824, articleTitle=null, refAbstract=null), Reference(id=1327013241349321592, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=65, rfOrder=64, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Hao, Gong Dihong, Li Zhifeng, et al. Decorrelated adversarial learning for age-invariant face recognition[C]//Proc of the 2019 IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 3522−3531, articleTitle=null, refAbstract=null), Reference(id=1327013241491927929, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=66, rfOrder=65, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhong Yaoyao, Deng Weihong. Adversarial learning with margin-based triplet embedding regularization[C]//Proc of the 2019 IEEE/CVF Int Conf on Computer Vision. Piscataway, NJ: IEEE, 2019: 6548−6557, articleTitle=null, refAbstract=null), Reference(id=1327013241596785530, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=67, rfOrder=66, 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=1327013241689060219, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=68, rfOrder=67, authorNames=null, journalName=null, refType=null, unstructuredReference=Bai Tao, Luo Jinqi, Zhao Jun, et al. Recent advances in adversarial training for adversarial robustness[C]//Proc of the 21st Int Joint Conf on Artificial Intelligence. Piscataway, NJ: IEEE, 2021: 4312−4321, articleTitle=null, refAbstract=null), Reference(id=1327013241772946301, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=69, rfOrder=68, authorNames=null, journalName=null, refType=null, unstructuredReference=Tramèr F, Kurakin A, Papernot N, et al. Ensemble adversarial training: attacks and defenses[J]. arXiv preprint, arXiv: 1705.07204, 2017, articleTitle=null, refAbstract=null), Reference(id=1327013241852638079, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=70, rfOrder=69, authorNames=null, journalName=null, refType=null, unstructuredReference=Carlini N, Wagner D. Audio adversarial examples: Targeted attacks on speech-to-text[C/OL]//Proc of the 2018 IEEE Security and Privacy Workshops. Piscataway, NJ: IEEE, 2018[2023-02-02]. https://ieeexplor e.ieee.org/abstract/document/8424625/, articleTitle=null, refAbstract=null), Reference(id=1327013241940718464, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=71, rfOrder=70, authorNames=null, journalName=null, refType=null, unstructuredReference=Hannun A, Case C, Casper J, et al. Deep speech: Scaling up end-to-end speech recognition[J]. arXiv preprint, arXiv: 1412.5567, 2014, articleTitle=null, refAbstract=null), Reference(id=1327013242028798849, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=72, rfOrder=71, authorNames=null, journalName=null, refType=null, unstructuredReference=郑海斌,陈晋音,章燕. 面向自然语言处理的对抗攻防与鲁棒性分析综述[J]. 计算机研究与发展,2021,58(8):1727−1750, articleTitle=null, refAbstract=null), Reference(id=1327013243706520450, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=72, rfOrder=72, authorNames=null, journalName=null, refType=null, unstructuredReference=Zheng Haibin, Chen Jinyin, Zhang Yan. Survey of adversarial attack, defense and robustness analysis for natural language processing[J]. Journal of Computer Research and Development, 2021, 58(8): 1727−1750 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327013243815572355, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=73, rfOrder=73, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang W E, Sheng Q Z, Alhazmi A, et al. Adversarial attacks on deep-learning models in natural language processing: A survey[J]. ACM Transactions on Intelligent Systems and Technology, 2020, 11(3): 1−41, articleTitle=null, refAbstract=null), Reference(id=1327013243895264132, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=74, rfOrder=74, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Yi, Zheng Xiaoqing, Hsieh C J, et al. Defense against adversarial attacks in NLP via dirichlet neighborhood ensemble[J]. arXiv preprint, arXiv: 2006.11627, 2020, articleTitle=null, refAbstract=null), Reference(id=1327013243966567301, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=75, rfOrder=75, authorNames=null, journalName=null, refType=null, unstructuredReference=Araujo V, Carvallo A, Aspillaga C, et al. On adversarial examples for biomedical NLP tasks[J]. arXiv preprint, arXiv: 2004.11157, 2020, articleTitle=null, refAbstract=null), Reference(id=1327013244084007814, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=76, rfOrder=76, authorNames=null, journalName=null, refType=null, unstructuredReference=Miao Deshui, Zhang Jiaqi, Xie Wenbo, et al. Simple contrastive representation adversarial learning for NLP tasks[J]. arXiv preprint, arXiv: 2111.13301, 2021, articleTitle=null, refAbstract=null), Reference(id=1327013244193059719, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=77, rfOrder=77, authorNames=null, journalName=null, refType=null, unstructuredReference=Han Xudong, Baldwin T, Cohn T. Decoupling adversarial training for fair NLP[C/OL]//Proc of the Joint Conf of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Int Joint Conf on Natural Language Processing(ACL-IJCNLP 2021). 2021: 471−477. [2023-02-02]. https://aclanthology.org/2021.findings-acl.41.pdf, articleTitle=null, refAbstract=null), Reference(id=1327013244281140104, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=78, rfOrder=78, authorNames=null, journalName=null, refType=null, unstructuredReference=Kim B, Sagduyu Y E, Davaslioglu K, et al. Over-the-air adversarial attacks on deep learning based modulation classifier over wireless channels[C/OL]//Proc of the 54th Annual Conf on Information Sciences and Systems(CISS). Piscataway, NJ: IEEE, 2020[2023-02-02]. https://ieeexplore.ieee.org/abstract/document/9086166/, articleTitle=null, refAbstract=null), Reference(id=1327013244373414793, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=79, rfOrder=79, authorNames=null, journalName=null, refType=null, unstructuredReference=Restuccia F, D’Oro S, Al-Shawabka A, et al. Generalized wireless adversarial deep learning[C]//Proc of the 2nd ACM Workshop on Wireless Security and Machine Learning. New York: ACM, 2020: 49−54, articleTitle=null, refAbstract=null), Reference(id=1327013244444717962, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=80, rfOrder=80, authorNames=null, journalName=null, refType=null, unstructuredReference=Bair S, DelVecchio M, Flowers B, et al. On the limitations of targeted adversarial evasion attacks against deep learning enabled modulation recognition[C/OL]//Proc of the ACM Workshop on Wireless Security and Machine Learning. New York: ACM, 2019: 25−30, articleTitle=null, refAbstract=null), Reference(id=1327013244516021131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=81, rfOrder=81, authorNames=null, journalName=null, refType=null, unstructuredReference=Kokalj-Filipovic S, Miller R, Morman J. Targeted adversarial examples against RF deep classifiers[C]//Proc of the ACM Workshop on Wireless Security and Machine Learning. New York: ACM, 2019: 6−11, articleTitle=null, refAbstract=null), Reference(id=1327013244599907212, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=82, rfOrder=82, authorNames=null, journalName=null, refType=null, unstructuredReference=Ke Da, Huang Zhitao, Wang Xiang, et al. Application of adversarial examples in communication modulation classification[C]//Proc of the 19th Int Conf on Data Mining Workshops. Piscataway, NJ: IEEE, 2019: 877−882, articleTitle=null, refAbstract=null), Reference(id=1327013244679598989, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=83, rfOrder=83, authorNames=null, journalName=null, refType=null, unstructuredReference=Davaslioglu K, Sagduyu Y E. Trojan attacks on wireless signal classification with adversarial machine learning[C/OL]//Proc of the 12th IEEE Int Symp on Dynamic Spectrum Access Networks. Piscataway, NJ: IEEE, 2019[2023-02-02]. https://ieeexplore.ieee.org/abstract/document/8935782/, articleTitle=null, refAbstract=null), Reference(id=1327013244742513550, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=84, rfOrder=84, authorNames=null, journalName=null, refType=null, unstructuredReference=Kim B, Sagduyu Y E, Erpek T, et al. Adversarial attacks with multiple antennas against deep learning-based modulation classifiers[C/OL]//Proc of the 2020 IEEE Globecom Workshops. Piscataway, NJ: IEEE, 2020[2023-02-02]. https://ieeexplore.ieee.org/abstract/document/9367473/, articleTitle=null, refAbstract=null), Reference(id=1327013244813816719, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=85, rfOrder=85, authorNames=null, journalName=null, refType=null, unstructuredReference=Yi Jinho, Gamal A E. Gradient-based adversarial deep modulation classification with data-driven subsampling[J]. arXiv preprint, arXiv: 2104.06375, 2021, articleTitle=null, refAbstract=null), Reference(id=1327013244910285712, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=86, rfOrder=86, authorNames=null, journalName=null, refType=null, unstructuredReference=Usama M, Asim M, Qadir J, et al. Adversarial machine learning attack on modulation classification[C/OL]//Proc of the 2019 UK/ China Emerging Technologies. Piscataway, NJ: IEEE, 2019[2023-02-02]. https://ieeexpl ore.ieee.org/abstract/document/8881843, articleTitle=null, refAbstract=null), Reference(id=1327013245094835089, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=87, rfOrder=87, authorNames=null, journalName=null, refType=null, unstructuredReference=Usama M, Qadir J, Al-Fuqaha A. Black-box adversarial ML attack on modulation classification[J]. arXiv preprint, arXiv: 1908.00635, 2019, articleTitle=null, refAbstract=null), Reference(id=1327013245224858515, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=88, rfOrder=88, authorNames=null, journalName=null, refType=null, unstructuredReference=Sahay R, Brinton C G, Love D J. Frequency-based automated modulation classification in the presence of adversaries[C/OL]//Proc of the 56th IEEE Int Conf on Communications. Piscataway, NJ: IEEE, 2021[2023-02-02]. https://ieeexplore.ieee.org/abstract/document/9500583/, articleTitle=null, refAbstract=null), Reference(id=1327013245312938900, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=89, rfOrder=89, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Yun, Zhao Haojun, Tu Ya, et al. Threats of adversarial attacks in DNN-based modulation recognition[C]//Proc of the 39th IEEE Conf on Computer Communications. Piscataway, NJ: IEEE, 2020: 2469−2478, articleTitle=null, refAbstract=null), Reference(id=1327013245421990805, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=90, rfOrder=90, authorNames=null, journalName=null, refType=null, unstructuredReference=Hameed M Z, Gyorgy A, Gunduz D. Communication without interception: Defense against modulation detection[C/OL]//Proc of the 7th IEEE Global Conf on Signal and Information Processing. Piscataway, NJ: IEEE, 2019[2023-02-02]. https://ieeexplore.ieee.org/abstract/document/8969541/, articleTitle=null, refAbstract=null), Reference(id=1327013245531042710, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=91, rfOrder=91, authorNames=null, journalName=null, refType=null, unstructuredReference=Hameed M Z, Gyorgy A, Gunduz D. The best defense is a good offense: Adversarial attacks to avoid modulation detection[J]. IEEE Transactions on Information Forensics and Security, 2021, 16: 1074−1087, articleTitle=null, refAbstract=null), Reference(id=1327013245774312343, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=92, rfOrder=92, authorNames=null, journalName=null, refType=null, unstructuredReference=DelVecchio M, Flowers B, Headley W C. Effects of forward error correction on communications aware evasion attacks[C/OL]//Proc of the 31st Annual Int Symp on Personal, Indoor and Mobile Radio Communications. Piscataway, NJ: IEEE, 2020[2023-02-02]. https://ieeexplore.ieee.org/abst ract/document/9217343/, articleTitle=null, refAbstract=null), Reference(id=1327013245883364248, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=93, rfOrder=93, authorNames=null, journalName=null, refType=null, unstructuredReference=DelVecchio M, Arndorfer V, Headley W C. Investigating a spectral deception loss metric for training machine learning-based evasion attacks[C]//Proc of the 2nd ACM Workshop on Wireless Security and Machine Learning. New York: ACM, 2020: 43−48, articleTitle=null, refAbstract=null), Reference(id=1327013245967250329, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=94, rfOrder=94, authorNames=null, journalName=null, refType=null, unstructuredReference=Hameed M Z. New quality measures for adversarial attacks with applications to secure communication[D]. London: Imperial College London, 2020, articleTitle=null, refAbstract=null), Reference(id=1327013246093079450, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=95, rfOrder=95, authorNames=null, journalName=null, refType=null, unstructuredReference=Berian A, Staab K, Ditzler G, et al. Adversarial filters for secure modulation classification[C]//Proc of the 55th Asilomar Conf on Signals, Systems, and Computers. Piscataway, NJ: IEEE, 2021: 361−367, articleTitle=null, refAbstract=null), Reference(id=1327013246189548443, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=96, rfOrder=96, authorNames=null, journalName=null, refType=null, unstructuredReference=Sandler R A, Relich P K, Cho C, et al. Real-time over-the-air adversarial perturbations for digital communications using deep neural networks[J]. arXiv preprint, arXiv: 2202.11197, 2022, articleTitle=null, refAbstract=null), Reference(id=1327013246260851612, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=97, rfOrder=97, authorNames=null, journalName=null, refType=null, unstructuredReference=Chakraborty A, Alam M, Dey V, et al. Adversarial attacks and defences: A survey[J]. arXiv preprint, arXiv: 1810.00069, 2018, articleTitle=null, refAbstract=null), Reference(id=1327013246340543389, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=98, rfOrder=98, authorNames=null, journalName=null, refType=null, unstructuredReference=Yi Shi, Sagduyu Y, Grushin A. How to steal a machine learning classifier with deep learning[C/OL]//Proc of the 2017 IEEE Int Symp on Technologies for Homeland Security. Piscataway, NJ: IEEE, 2017[2023-02-02]. https://ieeexplore.ieee.org/abstract/document/7943475/, articleTitle=null, refAbstract=null), Reference(id=1327013246411846558, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=99, rfOrder=99, authorNames=null, journalName=null, refType=null, unstructuredReference=Shi Y, Sagduyu Y E, Davaslioglu K, et al. Active deep learning attacks under strict rate limitations for online API calls[C/OL]//Proc of the 2018 IEEE Int Symp on Technologies for Homeland Security. Piscataway, NJ: IEEE, 2018[2023-02-02]. https://ieeexplore.ieee.org/abstract/document/8574124/, articleTitle=null, refAbstract=null), Reference(id=1327013246529287071, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=100, rfOrder=100, authorNames=null, journalName=null, refType=null, unstructuredReference=Pi Lei, Lu Zhuo, Sagduyu Y, et al. Defending active learning against adversarial inputs in automated document classification[C]//Proc of the 4th IEEE Global Conf on Signal and Information Processing. Piscataway, NJ: IEEE, 2016: 257−261, articleTitle=null, refAbstract=null), Reference(id=1327013248316060576, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=101, rfOrder=101, authorNames=null, journalName=null, refType=null, unstructuredReference=Shi Yi, Sagduyu Y E, Davaslioglu K, et al. Generative adversarial networks for black-box API attacks with limited training data[C]//Proc of the 2018 IEEE Int Symp on Signal Processing and Information Technology. Piscataway, NJ: IEEE, 2018: 453−458, articleTitle=null, refAbstract=null), Reference(id=1327013248471249825, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=102, rfOrder=102, authorNames=null, journalName=null, refType=null, unstructuredReference=Biggio B, Nelson B, Laskov P. Poisoning attacks against support vector machines[J]. arXiv preprint, arXiv: 1206.6389, 2012, articleTitle=null, refAbstract=null), Reference(id=1327013248563524514, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=103, rfOrder=103, 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 the 40th IEEE Symp on Security and Privacy. Piscataway, NJ: IEEE, 2019: 707−723, articleTitle=null, refAbstract=null), Reference(id=1327013248714519459, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=104, rfOrder=104, authorNames=null, journalName=null, refType=null, unstructuredReference=Kurakin A, Goodfellow I J, Bengio S. Adversarial examples in the physical world[J]. arXiv preprint, arXiv: 1607.02533, articleTitle=null, refAbstract=null), Reference(id=1327013248794211236, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=105, rfOrder=105, authorNames=null, journalName=null, refType=null, unstructuredReference=Kim B, Sagduyu Y E, Erpek T, et al. Channel effects on surrogate models of adversarial attacks against wireless signal classifiers[C/OL]//Proc of the 57th IEEE Int Conf on Communications. Piscataway, NJ: IEEE, 2021[2023-02-02]. https://ieeexplore.ieee.org/abstract/document/9500374/, articleTitle=null, refAbstract=null), Reference(id=1327013248903263141, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=106, rfOrder=106, authorNames=null, journalName=null, refType=null, unstructuredReference=Wyner A D. The wire-tap channel[J]. Bell System Technical Journal, 1975, 54(8): 1355−1387, articleTitle=null, refAbstract=null), Reference(id=1327013248974566310, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=107, rfOrder=107, authorNames=null, journalName=null, refType=null, unstructuredReference=Gunduz D, Brown D R, Poor H V. Secret communication with feedback[C/OL]//Proc of the Int Symp on Information Theory and Its Applications. Piscataway, NJ: IEEE, 2008[2023-02-02]. https://ieeexplor e.ieee.org/abstract/document/4895417/, articleTitle=null, refAbstract=null), Reference(id=1327013249062646695, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=108, rfOrder=108, authorNames=null, journalName=null, refType=null, unstructuredReference=Papernot N, McDaniel P, Jha S, et al. The limitations of deep learning in adversarial settings[C]//Proc of the 1st IEEE European Symp on Security and Privacy. Piscataway, NJ: IEEE, 2016: 372−387, articleTitle=null, refAbstract=null), Reference(id=1327013249133949864, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=109, rfOrder=109, authorNames=null, journalName=null, refType=null, unstructuredReference=Kim B, Sagduyu Y E, Davaslioglu K, et al. How to make 5G communications “Invisible”: Adversarial machine learning for wireless privacy[C]//Proc of the 54th Asilomar Conf on Signals, Systems, and Computers. Piscataway, NJ: IEEE, 2020: 763−767, articleTitle=null, refAbstract=null), Reference(id=1327013249196864425, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=110, rfOrder=110, authorNames=null, journalName=null, refType=null, unstructuredReference=Baluja S, Fischer I. Learning to attack: Adversarial transformation networks[C/OL]//Proc of the AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2018[2023-02-02]. https://ojs.aaai.org/index.php/AAAI/article/view/11672, articleTitle=null, refAbstract=null), Reference(id=1327013249268167594, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=111, rfOrder=111, authorNames=null, journalName=null, refType=null, unstructuredReference=张田,杨奎武,魏江宏. 面向图像数据的对抗样本检测与防御技术综述[J]. 计算机研究与发展,2022,59(6):1315−1328, articleTitle=null, refAbstract=null), Reference(id=1327013249373025195, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=111, rfOrder=112, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Tian, Yang Kuiwu, Wei Jianghong. Survey on detecting and defending adversarial examples for image data[J]. Journal of Computer Research and Development, 2022, 59(6): 1315−1328 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327013249477882796, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=112, rfOrder=113, authorNames=null, journalName=null, refType=null, unstructuredReference=Dong Yinpeng, Liao Fangzhou, Pang Tianyu, et al. Boosting adversarial attacks with momentum[C]//Proc of the 31st IEEE/CVF Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 9185−9193, articleTitle=null, refAbstract=null), Reference(id=1327013249561768878, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=113, rfOrder=114, authorNames=null, journalName=null, refType=null, unstructuredReference=Moosavi-Dezfooli S M, Fawzi A, Fawzi O, et al. Universal adversarial perturbations[C]//Proc of the 30th IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2017: 86−94, articleTitle=null, refAbstract=null), Reference(id=1327013249654043567, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=114, rfOrder=115, authorNames=null, journalName=null, refType=null, unstructuredReference=Carlini N, Wagner D. Towards evaluating the robustness of neural networks[C]//Proc of the 38th IEEE Symp on Security and Privacy. Piscataway, NJ: IEEE, 2017: 39−57, articleTitle=null, refAbstract=null), Reference(id=1327013249721152432, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=115, rfOrder=116, authorNames=null, journalName=null, refType=null, unstructuredReference=Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network[J]. arXiv preprint, arXiv: 1503.02531, 2015, articleTitle=null, refAbstract=null), Reference(id=1327013249788261297, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=116, rfOrder=117, authorNames=null, journalName=null, refType=null, unstructuredReference=Papernot N, Faghri F, Carlini N, et al. Technical report on the CleverHans v2.1. 0 adversarial examples library[J]. arXiv preprint, arXiv: 1610.00768, 2016, articleTitle=null, refAbstract=null), Reference(id=1327013249863758770, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=117, rfOrder=118, authorNames=null, journalName=null, refType=null, unstructuredReference=Ramjee S, Ju Shengtai, Yang Diyu, et al. Ensemble wrapper subsampling for deep modulation classification[J]. IEEE Transactions on Cognitive Communications and Networking, 2021, 7(4): 1156−1170, articleTitle=null, refAbstract=null), Reference(id=1327013249989587891, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=118, rfOrder=119, authorNames=null, journalName=null, refType=null, unstructuredReference=Kurakin A, Goodfellow I J, Bengio S. Adversarial machine learning at scale[C/OL]//Proc of Int Conf on Learning Representations.[2024-05-26]. https://openreview.net/forum?id=BJm4T4Kgx, articleTitle=null, refAbstract=null), Reference(id=1327013250065085364, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=119, rfOrder=120, authorNames=null, journalName=null, refType=null, unstructuredReference=Sagduyu Y E, Shi Yi, Erpek T. Adversarial deep learning for over-the-air spectrum poisoning attacks[J]. IEEE Transactions on Mobile Computing, 2021, 20(2): 306−319, articleTitle=null, refAbstract=null), Reference(id=1327013250178331573, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=120, rfOrder=121, authorNames=null, journalName=null, refType=null, unstructuredReference=Shi Yi, Erpek T, Sagduyu Y E, et al. Spectrum data poisoning with adversarial deep learning[C]//Proc of the 37th IEEE Military Communications Conf. Piscataway, NJ: IEEE, 2018: 407−412, articleTitle=null, refAbstract=null), Reference(id=1327013250258023350, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=121, rfOrder=122, authorNames=null, journalName=null, refType=null, unstructuredReference=Bengio Y, Louradour J, Collobert R, et al. Curriculum learning[C]//Proc of the 26th Annual Int Conf on Machine Learning. New York: ACM, 2009: 41−48, articleTitle=null, refAbstract=null), Reference(id=1327013250371269559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=122, rfOrder=123, authorNames=null, journalName=null, refType=null, unstructuredReference=Cohen J, Rosenfeld E, Kolter J Z. Certified adversarial robustness via randomized smoothing[C]//Proc of the 36th Int Conf on Machine Learning. New York: PMLR. 2019: 1310−1320, articleTitle=null, refAbstract=null), Reference(id=1327013250434184120, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=123, rfOrder=124, authorNames=null, journalName=null, refType=null, unstructuredReference=Dodge Y. Kolmogorov–Smirnov test[J/OL]. The Concise Encyclopedia of Statistics, 2008[2023-03-08]. http://link.springer.com/10.1007/978-0-387-32 833-1_214, articleTitle=null, refAbstract=null), Reference(id=1327013250555818937, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=124, rfOrder=125, authorNames=null, journalName=null, refType=null, unstructuredReference=Al-shawabka A, Restuccia F, D’Oro S, et al. Massive-scale I/Q datasets for WiFi radio fingerprinting[J]. Computer Networks, 2020, 182: 107566, articleTitle=null, refAbstract=null), Reference(id=1327013250652287930, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=125, rfOrder=126, authorNames=null, journalName=null, refType=null, unstructuredReference=Alkhateeb A. DeepMIMO: A generic deep learning dataset for millimeter wave and massive MIMO applications[J]. arXiv preprint, arXiv: 1902.06435, 2019, articleTitle=null, refAbstract=null), Reference(id=1327013250752951227, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=126, rfOrder=127, authorNames=null, journalName=null, refType=null, unstructuredReference=Ezuma M, Erden F, Anjinappa C, et al. Drone remote controller RF signal dataset [DB/OL]. IEEE DataPort, 2020[2023-03-08]. https://ieee-dataport.org/open-access/drone-remote-controller-rf-signal-dataset, articleTitle=null, refAbstract=null), Reference(id=1327013250836837309, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=127, rfOrder=128, authorNames=null, journalName=null, refType=null, unstructuredReference=Ilyas A, Santurkar S, Tsipras D, et al. Adversarial examples are not bugs, they are features[J/OL]. Advances in Neural Information Processing Systems, 2019[2023-03-08]. https://proceedings.neurips.cc/paper/2019/has h/e2c420d928d4bf8ce0ff2ec19b371514-Abstract.html, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1327013209531331275, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, xref=1, ext=[AuthorCompanyExt(id=1327013209564885708, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1Beijing Key Laboratory of Security and Privacy in Intelligent Transportation (Beijing Jiaotong University), Beijing 100044), AuthorCompanyExt(id=1327013209577468621, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209531331275, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
1智能交通数据安全与隐私保护北京市重点实验室(北京交通大学) 北京 100044)]), AuthorCompany(id=1327013209669743310, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, xref=2, ext=[AuthorCompanyExt(id=1327013209682326223, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209669743310, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190), AuthorCompanyExt(id=1327013209690714832, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, companyId=1327013209669743310, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=
2中国科学院计算技术研究所智能信息处理重点实验室 北京 100190)])], figs=[ArticleFig(id=1327013216850391820, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, label=Figure 1, caption=
Overall structural diagram, figureFileSmall=UFzhSH9esIpOdlBe/yRwDQ==, figureFileBig=uZuRLJsLjmpg2hfJ0sWojQ==, tableContent=null), ArticleFig(id=1327013216972026638, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, label=图1, caption=
整体架构图, figureFileSmall=UFzhSH9esIpOdlBe/yRwDQ==, figureFileBig=uZuRLJsLjmpg2hfJ0sWojQ==, tableContent=null), ArticleFig(id=1327013217349513999, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, label=Figure 2, caption=
Structure diagram of wireless communication system and signal modulation recognition based on DL, figureFileSmall=Q4+9z3IjDiK/1e+YDjW2mA==, figureFileBig=h1nU5cSM+rH/EOME1YZdSQ==, tableContent=null), ArticleFig(id=1327013217445982992, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, label=图2, caption=
无线通信系统与基于深度学习的信号调制识别结构图, figureFileSmall=Q4+9z3IjDiK/1e+YDjW2mA==, figureFileBig=h1nU5cSM+rH/EOME1YZdSQ==, tableContent=null), ArticleFig(id=1327013217521480465, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, label=Figure 3, caption=
Representative DL models for modulation recognition, figureFileSmall=QfNevUNgQhUHYil4kvzBRA==, figureFileBig=ZYiRHaM1BfBNCEXzi2B3Ow==, tableContent=null), ArticleFig(id=1327013219480220434, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, label=图3, caption=
面向调制识别的代表性深度学习模型, figureFileSmall=QfNevUNgQhUHYil4kvzBRA==, figureFileBig=ZYiRHaM1BfBNCEXzi2B3Ow==, tableContent=null), ArticleFig(id=1327013219765433107, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, label=Figure 4, caption=
Categorization framework diagram based on adversarial deep learning, figureFileSmall=/Fg99Tc4QugCSXOMfiiXtA==, figureFileBig=gnqVRnIXKptxXXFy8kgx4Q==, tableContent=null), ArticleFig(id=1327013221359268629, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, label=图4, caption=
基于对抗深度学习的分类框架图, figureFileSmall=/Fg99Tc4QugCSXOMfiiXtA==, figureFileBig=gnqVRnIXKptxXXFy8kgx4Q==, tableContent=null), ArticleFig(id=1327013221548012311, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, label=Figure 5, caption=
Comparison of physical adversarial attack model and digital adversarial attack model, figureFileSmall=hdwtuOPl+yNg3uB/ClRxiQ==, figureFileBig=QUGNfYVOn6JlOSnRk82opw==, tableContent=null), ArticleFig(id=1327013221732561689, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, label=图5, caption=
物理对抗攻击模型与数字对抗攻击模型对比, figureFileSmall=hdwtuOPl+yNg3uB/ClRxiQ==, figureFileBig=QUGNfYVOn6JlOSnRk82opw==, tableContent=null), ArticleFig(id=1327013221870973722, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, label=Figure 6, caption=
Threat model of adversarial attack based on signal modulation recognition, figureFileSmall=tZFyGLVWYXbd2wz/m+FONw==, figureFileBig=AurtyF7CM1L7xa0mbWRbWw==, tableContent=null), ArticleFig(id=1327013221988414235, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, label=图6, caption=
基于信号调制识别的对抗攻击威胁模型, figureFileSmall=tZFyGLVWYXbd2wz/m+FONw==, figureFileBig=AurtyF7CM1L7xa0mbWRbWw==, tableContent=null), ArticleFig(id=1327013222093271836, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, label=Figure 7, caption=
Two adversarial attack scenarios considering channel effect, figureFileSmall=xztuGtrzo1E7TmSq/T/Hog==, figureFileBig=RdrXG9rmdabYneYeGjih2g==, tableContent=null), ArticleFig(id=1327013222172963613, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, label=图7, caption=
考虑信道效应的2种对抗攻击场景, figureFileSmall=xztuGtrzo1E7TmSq/T/Hog==, figureFileBig=RdrXG9rmdabYneYeGjih2g==, tableContent=null), ArticleFig(id=1327013222332347166, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, label=Table 1, caption=
Summary of Main Open-Source Datasets for Signal Modulation Recognition, figureFileSmall=null, figureFileBig=null, tableContent=
| 数据集 | 调制方式 | 样本大小 | 样本总数 | SNR/dB |
|---|
| RML2016.10A | 11类 (8PSK, BPSK, CPFSK, GFSK, PAM4, 16QAM, AM-DSB, AM-SSB, 64QAM, QPSK, WBFM) | 2 × 128 | 220 000 | −20~18 |
| RML2016.10B | 10类 (8PSK, BPSK, CPFSK, GFSK, PAM4, AM-DSB, 16QAM, 64QAM, QPSK, WBFM) | 2 × 128 | 1 200 000 | −20~18 |
| RML2016.04C | 11类 (8PSK, BPSK, CPFSK, GFSK, PAM4, AM-DSB, AM-SSB, 16QAM, 64QAM, QPSK, WBFM) | 2 × 128 | 162 060 | −20~18 |
| RML2018.01A | 24类 (OOK, 4ASK, 8ASK, BPSK, QPSK, 8PSK, 16PSK, 32PSK, 16APSK, 32APSK, 64APSK, 128APSK, 16QAM, 32QAM, 64QAM, 128QAM, 256QAM, AM-SSB-WC, AM-SSB-SC, AM-DSB-WC, AM-DSB-SC, FM, GMASK, OQPSK) | 2 × 1 024 | 2 555 904 | −20~10 |
| HisarMod2019.1 | 26类 (AM-DSB, AM-SC, AM-USB, AM-LSB, FM, PM, 2FSK, 4FSK, 8FSK, 16FSK, 4PAM, 8PAM, 16PAM, BPSK, QPSK, 8PSK, 16PSK, 32PSK, 64PSK, 4QAM, 8QAM, 16QAM, 32QAM, 64QAM, 128QAM, 256QAM) | 2 × 1 024 | 780 000 | −20~18 |
), ArticleFig(id=1327013222420427551, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, label=表1, caption=
信号调制识别主要的开源数据集汇总
, figureFileSmall=null, figureFileBig=null, tableContent=
| 数据集 | 调制方式 | 样本大小 | 样本总数 | SNR/dB |
|---|
| RML2016.10A | 11类 (8PSK, BPSK, CPFSK, GFSK, PAM4, 16QAM, AM-DSB, AM-SSB, 64QAM, QPSK, WBFM) | 2 × 128 | 220 000 | −20~18 |
| RML2016.10B | 10类 (8PSK, BPSK, CPFSK, GFSK, PAM4, AM-DSB, 16QAM, 64QAM, QPSK, WBFM) | 2 × 128 | 1 200 000 | −20~18 |
| RML2016.04C | 11类 (8PSK, BPSK, CPFSK, GFSK, PAM4, AM-DSB, AM-SSB, 16QAM, 64QAM, QPSK, WBFM) | 2 × 128 | 162 060 | −20~18 |
| RML2018.01A | 24类 (OOK, 4ASK, 8ASK, BPSK, QPSK, 8PSK, 16PSK, 32PSK, 16APSK, 32APSK, 64APSK, 128APSK, 16QAM, 32QAM, 64QAM, 128QAM, 256QAM, AM-SSB-WC, AM-SSB-SC, AM-DSB-WC, AM-DSB-SC, FM, GMASK, OQPSK) | 2 × 1 024 | 2 555 904 | −20~10 |
| HisarMod2019.1 | 26类 (AM-DSB, AM-SC, AM-USB, AM-LSB, FM, PM, 2FSK, 4FSK, 8FSK, 16FSK, 4PAM, 8PAM, 16PAM, BPSK, QPSK, 8PSK, 16PSK, 32PSK, 64PSK, 4QAM, 8QAM, 16QAM, 32QAM, 64QAM, 128QAM, 256QAM) | 2 × 1 024 | 780 000 | −20~18 |
), ArticleFig(id=1327013222630142753, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, label=Table 2, caption=
Signal Modulation Recognition for Deep Learning Models, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型类型 | 模型名称 | 优点 | 缺点 |
|---|
无监督学 习模型 | SCF-DBN[39,42]、自编码器1[43]、自编码器2[44] | ·处理未标记数据; ·特征提取表现优异. | ·计算复杂性较高,限制大规模问题的应用; ·只用来测试少数调制方式分类,应用受限. |
前馈神经 网络模型 | FFNN1[40], FFNN2[45], FFNN3[46] | ·擅长提取高维特征; ·结构简单,优化灵活. | ·可能不适合处理如时间序列数据; ·需要大量训练数据,以避免过拟合. |
| CNN模型 | CNN1[4], CNN2[50], CNN3[51], ResNet[41], DenseNet[41], CM+CNN[47], SCNN[48], AlexNet[49], GoogLeNet[49], DrCNN[52], IC-AMCNet[56], MCNET[10] | ·强大的空间特征提取能力; ·适用于不同输入数据类型; ·高效架构满足低时延高可靠. | ·高计算复杂度,增加训练成本; ·可能忽略通信系统中固有的信号特征; ·原始I/Q信号直接输入模型导致信息损失. |
| RNN模型 | GRU[6], LSTM[7], DAE[57] | ·处理时间序列数据的能力; ·适用于低成本计算平台. | ·计算复杂度相对较高,训练难度较大; ·可能存在梯度消失或爆炸问题. |
| 混合模型 | CLDNN1[5], CLDNN2[41], MCLDNN[9], MLDNN[58], DBN+SNN[59] | ·结合CNN和RNN的优势; ·提高识别精度和泛化能力. | ·模型复杂性更高,计算和维护成本增加; ·计算资源需求更高. |
), ArticleFig(id=1327013222760166178, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, label=表2, caption=
信号调制识别的深度学习模型
, figureFileSmall=null, figureFileBig=null, tableContent=
| 模型类型 | 模型名称 | 优点 | 缺点 |
|---|
无监督学 习模型 | SCF-DBN[39,42]、自编码器1[43]、自编码器2[44] | ·处理未标记数据; ·特征提取表现优异. | ·计算复杂性较高,限制大规模问题的应用; ·只用来测试少数调制方式分类,应用受限. |
前馈神经 网络模型 | FFNN1[40], FFNN2[45], FFNN3[46] | ·擅长提取高维特征; ·结构简单,优化灵活. | ·可能不适合处理如时间序列数据; ·需要大量训练数据,以避免过拟合. |
| CNN模型 | CNN1[4], CNN2[50], CNN3[51], ResNet[41], DenseNet[41], CM+CNN[47], SCNN[48], AlexNet[49], GoogLeNet[49], DrCNN[52], IC-AMCNet[56], MCNET[10] | ·强大的空间特征提取能力; ·适用于不同输入数据类型; ·高效架构满足低时延高可靠. | ·高计算复杂度,增加训练成本; ·可能忽略通信系统中固有的信号特征; ·原始I/Q信号直接输入模型导致信息损失. |
| RNN模型 | GRU[6], LSTM[7], DAE[57] | ·处理时间序列数据的能力; ·适用于低成本计算平台. | ·计算复杂度相对较高,训练难度较大; ·可能存在梯度消失或爆炸问题. |
| 混合模型 | CLDNN1[5], CLDNN2[41], MCLDNN[9], MLDNN[58], DBN+SNN[59] | ·结合CNN和RNN的优势; ·提高识别精度和泛化能力. | ·模型复杂性更高,计算和维护成本增加; ·计算资源需求更高. |
), ArticleFig(id=1327013222856635171, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, label=Table 3, caption=
Function Expression of Adversarial Attack Methods, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 函数表示 | |
|---|
| 对抗攻击 | $\begin{aligned} &\mathop {{\text{min}}}\limits_{\boldsymbol {\theta} } {\left\| {\boldsymbol \delta } \right\|_p}\\[-4pt]&{\text{s}}{\text{.t}}{\text{. }}f({\boldsymbol {\theta} },{\boldsymbol {x}}) \ne f({\boldsymbol {\theta} },{\boldsymbol {x}} + {\boldsymbol \delta })\end{aligned}$ | (3) |
| 非针对性对抗攻击 | $\begin{aligned}& {\mathop {\max }\limits_{\boldsymbol {\theta} } \mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}} + {\boldsymbol \delta }),{{\boldsymbol y}^{{\text{true}}}})} \\[-4pt] &{{\text{s}}{\text{.t}}{\text{. }}\min {{\left\| {\boldsymbol \delta } \right\|}_p} \leqslant \varepsilon } \end{aligned}$ | (4) |
| 针对性对抗攻击 | $\begin{aligned}& {\mathop {\min }\limits_{\boldsymbol {\theta} } \mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}} + {\boldsymbol \delta }),{{\boldsymbol y}^{{\text{target}}}})} \\[-4pt] & {{\text{s}}{\text{.t}}{\text{. }}\min {{\left\| {\boldsymbol \delta } \right\|}_p} \leqslant \varepsilon } \end{aligned}$ | (5) |
), ArticleFig(id=1327013223074738981, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, label=表3, caption=
对抗攻击方法的函数表示
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 函数表示 | |
|---|
| 对抗攻击 | $\begin{aligned} &\mathop {{\text{min}}}\limits_{\boldsymbol {\theta} } {\left\| {\boldsymbol \delta } \right\|_p}\\[-4pt]&{\text{s}}{\text{.t}}{\text{. }}f({\boldsymbol {\theta} },{\boldsymbol {x}}) \ne f({\boldsymbol {\theta} },{\boldsymbol {x}} + {\boldsymbol \delta })\end{aligned}$ | (3) |
| 非针对性对抗攻击 | $\begin{aligned}& {\mathop {\max }\limits_{\boldsymbol {\theta} } \mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}} + {\boldsymbol \delta }),{{\boldsymbol y}^{{\text{true}}}})} \\[-4pt] &{{\text{s}}{\text{.t}}{\text{. }}\min {{\left\| {\boldsymbol \delta } \right\|}_p} \leqslant \varepsilon } \end{aligned}$ | (4) |
| 针对性对抗攻击 | $\begin{aligned}& {\mathop {\min }\limits_{\boldsymbol {\theta} } \mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}} + {\boldsymbol \delta }),{{\boldsymbol y}^{{\text{target}}}})} \\[-4pt] & {{\text{s}}{\text{.t}}{\text{. }}\min {{\left\| {\boldsymbol \delta } \right\|}_p} \leqslant \varepsilon } \end{aligned}$ | (5) |
), ArticleFig(id=1327013223196373799, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, label=Table 4, caption=
Summary of Adversarial Attack Function Experssion for Modulation Recognition, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 具体技术 | 对抗样本函数表示 | 优化目标函数表示 |
|---|
| FGM | FGSM [26] | ${{\boldsymbol {x}}^*} = {\boldsymbol {x}} + \varepsilon \times {\text{sgn}}\left( {{\nabla _{\boldsymbol {x}}}\mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}}),{\boldsymbol y})} \right)$ | $ \begin{aligned} &{\mathop {\max }\limits_{\boldsymbol {\theta} } \mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}} + {\boldsymbol \delta }),{{\boldsymbol y}^{{\text{true}}}})} \\ & {{\text{s}}{\text{.t}}{\text{. }}\min {{\left\| {\boldsymbol \delta } \right\|}_p} \leqslant \varepsilon }\end{aligned} $ |
| FGM [16] | ${{\boldsymbol {x}}^*} = {\boldsymbol {x}} + \varepsilon \times \dfrac{{{\nabla _{\boldsymbol {x}}}\mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}}),{\boldsymbol y})}}{{{{\left\| {{\nabla _{\boldsymbol {x}}}\mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}}),{\boldsymbol y})} \right\|}_2}}}$ | $ \begin{aligned} &{\mathop {\max }\limits_{\boldsymbol {\theta} } \mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}} + {\boldsymbol \delta }),{{\boldsymbol y}^{{\text{true}}}})} \\ & {{\text{s}}{\text{.t}}{\text{. }}\min {{\left\| {\boldsymbol \delta } \right\|}_p} \leqslant \varepsilon }\end{aligned} $ |
| FGM考虑信道效应[15] | ${{r}_{{\text{ar}}}} = {{\boldsymbol H}_{{\text{tr}}}}{\boldsymbol {x}} + {{\boldsymbol H}_{{\text{ar}}}}{\boldsymbol \delta } + {\boldsymbol n}$ | $ {\mathcal{L}(f({\boldsymbol {\theta} },{{r}_{{\text{ar}}}}),{{\boldsymbol y}^{{\text{target}}}}) \approx \mathcal{L}(f({\boldsymbol {\theta} },{{r}_{{\text{tr}}}}),{{\boldsymbol y}^{{\text{target}}}}) + }{{{({{\boldsymbol H}_{{\text{ar}}}}{\boldsymbol \delta })}^{\text{T}}}{\nabla _{\boldsymbol {x}}}\mathcal{L}(f({\boldsymbol {\theta} },{{r}_{{\text{tr}}}}),{{\boldsymbol y}^{{\text{target}}}})} $ |
| MI-FGSM | MI-FGSM [80] | $\begin{aligned} &{\boldsymbol {x}}_{t + 1}^* = {\boldsymbol {x}}_t^* + \left( {\dfrac{\varepsilon }{T}} \right) \times {\text{sgn}}({{\boldsymbol g}_{t + 1}})\\&{{\boldsymbol g}_{t + 1}} = \mu \times {{\boldsymbol g}_t} + \dfrac{{{\nabla _{\boldsymbol {x}}}\mathcal{L}(f({\boldsymbol {\theta} },{{\boldsymbol {x}}^*}),{\boldsymbol y})}}{{{{\left\| {{\nabla _{\boldsymbol {x}}}\mathcal{L}(f({\boldsymbol {\theta} },{{\boldsymbol {x}}^*}),{\boldsymbol y})} \right\|}_1}}}\end{aligned}$ | $ \begin{aligned} &{\mathop {\max }\limits_{\boldsymbol {\theta} } \mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}} + {\boldsymbol \delta }),{{\boldsymbol y}^{{\text{true}}}})} \\ & {{\text{s}}{\text{.t}}{\text{. }}\min {{\left\| {\boldsymbol \delta } \right\|}_p} \leqslant \varepsilon } \end{aligned}$ |
| PGD | PGD [91] | $ {{\boldsymbol {x}}}_{t+1}^{*}={\varPi }_{{\cal{B}}_{\epsilon}({{\boldsymbol {x}}}_{2})}({{\boldsymbol {x}}}_{t}^{*}+\beta \times \text{sgn}({\nabla }_{{\boldsymbol {x}}}{\mathcal{L}}(f(\boldsymbol{\theta},{{\boldsymbol {x}}}_{t}^{*}),{\boldsymbol y}))) $ | $ \begin{aligned} &{\mathop {\max }\limits_{\boldsymbol {\theta} } \mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}} + {\boldsymbol \delta }),{{\boldsymbol y}^{{\text{true}}}})} \\ & {{\text{s}}{\text{.t}}{\text{. }}\min {{\left\| {\boldsymbol \delta } \right\|}_p} \leqslant \varepsilon } \end{aligned}$ |
| C&W | Carlini & Wagner [81] | $ {{\boldsymbol {x}}^*} = {\boldsymbol {x}} + {\boldsymbol \delta } $ | $ \begin{aligned} &{\mathop {\min }\limits_{\boldsymbol \delta } \left\| {\boldsymbol \delta } \right\|_2^2 + c \times {f_t}({\boldsymbol {x}} + {\boldsymbol \delta })} \\ & {{\text{s}}{\text{.t}}{\text{. }}{\boldsymbol {x}} + {\boldsymbol \delta } \in {{\left[ {\left\lceil {\min ({x_i})} \right\rceil ,\left\lceil {\max ({x_i})} \right\rceil } \right]}^k}}\\&{f_t}({\boldsymbol x'}) = \max \left( {\max \{ Z{{({\boldsymbol x'})}_i}:i \ne t\} - Z{{({\boldsymbol x'})}_t},0} \right)\end{aligned} $ |
| ATN | P-ATN考虑通信损失[29] | ${{\boldsymbol {x}}^*} = {\boldsymbol {x}} + g({\boldsymbol {\theta} },{\boldsymbol {x}})$ | $ {\mathcal{L}( \cdot)= (1 - \alpha)\times {\mathcal{L}_{{\text{adv}}}}( \cdot)+ } {\alpha \times \left[ {\beta \times {\mathcal{L}_{{\text{comm}}}}( \cdot)+ (1 - \beta)\times {\mathcal{L}_{{\text{pwr}}}}( \cdot )} \right]} $ |
| AAE考虑通信损失[92] | ${{\boldsymbol {x}}^*} = g({\boldsymbol {\theta} },{\boldsymbol {x}})$ | ${\mathcal{L}_{{\text{total}}}} = \alpha \times {\mathcal{L}_{{\text{adv}}}} + \beta \times {\mathcal{L}_{{\text{comm}}}} + \gamma \times {\mathcal{L}_{{\text{pwr}}}}$ |
| BIM | BIM [89] | $ \begin{aligned} &{{{\boldsymbol {x}}_{t + 1}} = Cli{p_{{x, }\varepsilon }}\{ {{\boldsymbol {x}}_t} + } {\varepsilon \times {\text{sgn}}\left( {{\nabla _{\boldsymbol {x}}}\mathcal{L}(f({\boldsymbol {\theta} },{{\boldsymbol {x}}_t}),{{\boldsymbol y}_t})} \right)\} } \\ &Cli{p_{{{\boldsymbol{x}}, }\varepsilon }}\{ {\boldsymbol z}\} :{\boldsymbol z} \in [{\boldsymbol {x}} - \varepsilon ,{\boldsymbol {x}} + \varepsilon ] \end{aligned} $ | $ \begin{aligned} &{\mathop {\max }\limits_{\boldsymbol {\theta} } \mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}} + {\boldsymbol \delta }),{{\boldsymbol y}^{{\text{true}}}})} \\ & {{\text{s}}{\text{.t}}{\text{. }}\min {{\left\| {\boldsymbol \delta } \right\|}_p} \leqslant \varepsilon } \end{aligned}$ |
), ArticleFig(id=1327013223330591528, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, label=表4, caption=
面向调制识别的对抗攻击函数表达汇总
, figureFileSmall=null, figureFileBig=null, tableContent=
| 方法 | 具体技术 | 对抗样本函数表示 | 优化目标函数表示 |
|---|
| FGM | FGSM [26] | ${{\boldsymbol {x}}^*} = {\boldsymbol {x}} + \varepsilon \times {\text{sgn}}\left( {{\nabla _{\boldsymbol {x}}}\mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}}),{\boldsymbol y})} \right)$ | $ \begin{aligned} &{\mathop {\max }\limits_{\boldsymbol {\theta} } \mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}} + {\boldsymbol \delta }),{{\boldsymbol y}^{{\text{true}}}})} \\ & {{\text{s}}{\text{.t}}{\text{. }}\min {{\left\| {\boldsymbol \delta } \right\|}_p} \leqslant \varepsilon }\end{aligned} $ |
| FGM [16] | ${{\boldsymbol {x}}^*} = {\boldsymbol {x}} + \varepsilon \times \dfrac{{{\nabla _{\boldsymbol {x}}}\mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}}),{\boldsymbol y})}}{{{{\left\| {{\nabla _{\boldsymbol {x}}}\mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}}),{\boldsymbol y})} \right\|}_2}}}$ | $ \begin{aligned} &{\mathop {\max }\limits_{\boldsymbol {\theta} } \mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}} + {\boldsymbol \delta }),{{\boldsymbol y}^{{\text{true}}}})} \\ & {{\text{s}}{\text{.t}}{\text{. }}\min {{\left\| {\boldsymbol \delta } \right\|}_p} \leqslant \varepsilon }\end{aligned} $ |
| FGM考虑信道效应[15] | ${{r}_{{\text{ar}}}} = {{\boldsymbol H}_{{\text{tr}}}}{\boldsymbol {x}} + {{\boldsymbol H}_{{\text{ar}}}}{\boldsymbol \delta } + {\boldsymbol n}$ | $ {\mathcal{L}(f({\boldsymbol {\theta} },{{r}_{{\text{ar}}}}),{{\boldsymbol y}^{{\text{target}}}}) \approx \mathcal{L}(f({\boldsymbol {\theta} },{{r}_{{\text{tr}}}}),{{\boldsymbol y}^{{\text{target}}}}) + }{{{({{\boldsymbol H}_{{\text{ar}}}}{\boldsymbol \delta })}^{\text{T}}}{\nabla _{\boldsymbol {x}}}\mathcal{L}(f({\boldsymbol {\theta} },{{r}_{{\text{tr}}}}),{{\boldsymbol y}^{{\text{target}}}})} $ |
| MI-FGSM | MI-FGSM [80] | $\begin{aligned} &{\boldsymbol {x}}_{t + 1}^* = {\boldsymbol {x}}_t^* + \left( {\dfrac{\varepsilon }{T}} \right) \times {\text{sgn}}({{\boldsymbol g}_{t + 1}})\\&{{\boldsymbol g}_{t + 1}} = \mu \times {{\boldsymbol g}_t} + \dfrac{{{\nabla _{\boldsymbol {x}}}\mathcal{L}(f({\boldsymbol {\theta} },{{\boldsymbol {x}}^*}),{\boldsymbol y})}}{{{{\left\| {{\nabla _{\boldsymbol {x}}}\mathcal{L}(f({\boldsymbol {\theta} },{{\boldsymbol {x}}^*}),{\boldsymbol y})} \right\|}_1}}}\end{aligned}$ | $ \begin{aligned} &{\mathop {\max }\limits_{\boldsymbol {\theta} } \mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}} + {\boldsymbol \delta }),{{\boldsymbol y}^{{\text{true}}}})} \\ & {{\text{s}}{\text{.t}}{\text{. }}\min {{\left\| {\boldsymbol \delta } \right\|}_p} \leqslant \varepsilon } \end{aligned}$ |
| PGD | PGD [91] | $ {{\boldsymbol {x}}}_{t+1}^{*}={\varPi }_{{\cal{B}}_{\epsilon}({{\boldsymbol {x}}}_{2})}({{\boldsymbol {x}}}_{t}^{*}+\beta \times \text{sgn}({\nabla }_{{\boldsymbol {x}}}{\mathcal{L}}(f(\boldsymbol{\theta},{{\boldsymbol {x}}}_{t}^{*}),{\boldsymbol y}))) $ | $ \begin{aligned} &{\mathop {\max }\limits_{\boldsymbol {\theta} } \mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}} + {\boldsymbol \delta }),{{\boldsymbol y}^{{\text{true}}}})} \\ & {{\text{s}}{\text{.t}}{\text{. }}\min {{\left\| {\boldsymbol \delta } \right\|}_p} \leqslant \varepsilon } \end{aligned}$ |
| C&W | Carlini & Wagner [81] | $ {{\boldsymbol {x}}^*} = {\boldsymbol {x}} + {\boldsymbol \delta } $ | $ \begin{aligned} &{\mathop {\min }\limits_{\boldsymbol \delta } \left\| {\boldsymbol \delta } \right\|_2^2 + c \times {f_t}({\boldsymbol {x}} + {\boldsymbol \delta })} \\ & {{\text{s}}{\text{.t}}{\text{. }}{\boldsymbol {x}} + {\boldsymbol \delta } \in {{\left[ {\left\lceil {\min ({x_i})} \right\rceil ,\left\lceil {\max ({x_i})} \right\rceil } \right]}^k}}\\&{f_t}({\boldsymbol x'}) = \max \left( {\max \{ Z{{({\boldsymbol x'})}_i}:i \ne t\} - Z{{({\boldsymbol x'})}_t},0} \right)\end{aligned} $ |
| ATN | P-ATN考虑通信损失[29] | ${{\boldsymbol {x}}^*} = {\boldsymbol {x}} + g({\boldsymbol {\theta} },{\boldsymbol {x}})$ | $ {\mathcal{L}( \cdot)= (1 - \alpha)\times {\mathcal{L}_{{\text{adv}}}}( \cdot)+ } {\alpha \times \left[ {\beta \times {\mathcal{L}_{{\text{comm}}}}( \cdot)+ (1 - \beta)\times {\mathcal{L}_{{\text{pwr}}}}( \cdot )} \right]} $ |
| AAE考虑通信损失[92] | ${{\boldsymbol {x}}^*} = g({\boldsymbol {\theta} },{\boldsymbol {x}})$ | ${\mathcal{L}_{{\text{total}}}} = \alpha \times {\mathcal{L}_{{\text{adv}}}} + \beta \times {\mathcal{L}_{{\text{comm}}}} + \gamma \times {\mathcal{L}_{{\text{pwr}}}}$ |
| BIM | BIM [89] | $ \begin{aligned} &{{{\boldsymbol {x}}_{t + 1}} = Cli{p_{{x, }\varepsilon }}\{ {{\boldsymbol {x}}_t} + } {\varepsilon \times {\text{sgn}}\left( {{\nabla _{\boldsymbol {x}}}\mathcal{L}(f({\boldsymbol {\theta} },{{\boldsymbol {x}}_t}),{{\boldsymbol y}_t})} \right)\} } \\ &Cli{p_{{{\boldsymbol{x}}, }\varepsilon }}\{ {\boldsymbol z}\} :{\boldsymbol z} \in [{\boldsymbol {x}} - \varepsilon ,{\boldsymbol {x}} + \varepsilon ] \end{aligned} $ | $ \begin{aligned} &{\mathop {\max }\limits_{\boldsymbol {\theta} } \mathcal{L}(f({\boldsymbol {\theta} },{\boldsymbol {x}} + {\boldsymbol \delta }),{{\boldsymbol y}^{{\text{true}}}})} \\ & {{\text{s}}{\text{.t}}{\text{. }}\min {{\left\| {\boldsymbol \delta } \right\|}_p} \leqslant \varepsilon } \end{aligned}$ |
), ArticleFig(id=1327013223494169385, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, label=Table 5, caption=
Summary of Research Work on Digital/Physical Attacks for Different Adversarial Examples Generation Methods, figureFileSmall=null, figureFileBig=null, tableContent=
), ArticleFig(id=1327013223687107370, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, label=表5, caption=
针对不同对抗样本生成方法的数字攻击/物理攻击研究工作汇总
, figureFileSmall=null, figureFileBig=null, tableContent=
), ArticleFig(id=1327013223800353579, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, label=Table 6, caption=
Summary of Adversarial Samples Generation Methods for Modulation Recognition, figureFileSmall=null, figureFileBig=null, tableContent=
| 攻击方法 | 相关研究工作 | 关键技术 | 攻击分类 | 攻击目标 | 攻击能力 | 数据集 | 攻击后最低准确率/ %(SNR/dB) |
|---|
| 注:“-”为当前文献未给出较为明确的攻击后最低准确率. |
| FGM | Sadeghi等人[16] | 使用二分法改进FGM | 数字 | 非针对性 | 白盒 | RML2016.10A | 0 (10) |
| Kim等人[15,78] | 最大接收扰动功率算法MRPP改进FGM | 数字 | 针对性 | 白盒 | RML2016.10A | 13 (10) |
| 非针对性 | 白盒 | RML2016.10A | 17 (10) |
| Restuccia等人[79] | 在一组连续的输入信号切片上计算扰动 | 数字 | 针对性 | 白盒 | RML 2018.01A | - |
| 非针对性 | 白盒 | RML 2018.01A | 31 (0) |
| Kokalj-Filipovic[26] | 通过自编码器对调制识别模型进行预训练,提高模型鲁棒性 | 数字 | 非针对性 | 非适应性黑盒 | RML 2018.01A (BPSK, QPSK, 9-PSK) | 60 (14) |
| Ke等人[82] | FGSM和L-BFGS对抗攻击 | 数字 | 非针对性 | 白盒 | RML2016.04C | 21 (8) |
| Lin等人[20] | 比较多种方法性能,讨论波形变化 | 数字 | 非针对性 | 白盒 | RML2016.10A | 17 (10) |
| Kim等人[84] | 采用元素最大信道增益EMCG法来优化天线信号功率分配,生成并发对抗性扰动 | 数字 | 针对性 | 白盒 | RML2016.10A | 10 (10) |
| Sahay等人[88] | 基于频域特征分类,削弱非适应性黑盒对抗样本的可迁移性 | 数字 | 非针对性 | 白盒 | RML2016.10B | 23 (18) |
| 非针对性 | 非适应性黑盒 | RML2016.10B | 78 (18) |
| Lin等人[89] | 比较多种方法攻击性能,讨论调制类型鲁棒性 | 数字 | 非针对性 | 白盒 | RML2016.10A | 14 (10) |
| Flowers等人[19] | FGSM实现对抗攻击,并考虑接收器误码率 | 物理 | 非针对性 | 白盒 | RML2016.10A (BPSK) | 58 (10) |
| Berian等人[95] | 基于滤波器方法实现对抗攻击 | 物理 | 非针对性 | 白盒 | RML2016.10A | 25 (0) |
| MI-FGSM | Bair等人[80] | 利用MI-FGSM实现针对性(QPSK被误分为8PSK)与非针对性对抗攻击 | 数字 | 针对性 | 白盒 | RML2016.10A | 0 (18) |
| 非针对性 | 白盒 | RML2016.10A | 7 (18) |
| Lin等人[20] | 比较多种方法性能,讨论波形变化 | 数字 | 非针对性 | 白盒 | RML2016.10A | 10 (10) |
| Lin等人[89] | 比较多种方法攻击性能,讨论调制类型鲁棒性 | 数字 | 非针对性 | 白盒 | RML2016.10A | 10 (10) |
| PGD | Lin等人[20] | 比较多种方法性能,讨论波形变化 | 数字 | 非针对性 | 白盒 | RML2016.10A | 13 (10) |
| Lin等人[89] | 比较多种方法攻击性能,讨论调制类型鲁棒性 | 数字 | 非针对性 | 白盒 | RML2016.10A | 13 (10) |
| Sandler等人[96] | 利用PGD方法实现对抗攻击 | 数字 | 非针对性 | 白盒 | RML 2018.01A, 自建数据集 | - |
| Hameed等人[90] | PGD方法实现对抗攻击,考虑接收器误码率的影响,将l2范数随机噪声作为对照组 | 物理 | 非针对性 | 白盒 | 自建数据(QAM64) | 55 (10) |
| 非针对性 | 非适应性黑盒 | 自建数据(QAM64) | 55 (10) |
| Hameed等人[91] | 改进PGD方法,并通过降低传输速率来权衡误码率与分类精度 | 物理 | 非针对性 | 白盒 | 自建数据(QAM64) | 55 (10) |
| 非针对性 | 非适应性黑盒 | 自建数据(QAM64) | 72 (10) |
| Hameed [94] | 改进PGD方法,考虑误码率的优化 | 物理 | 非针对性 | 白盒 | 自建数据(QAM64) | 55 (10) |
| 非针对性 | 非适应性黑盒 | 自建数据(QAM64) | 72 (10) |
| Carlini & Wagner | Kokalj-Filipovic等人[81] | 改进Carlini&Wagner-l2方法以适应调制识别对抗攻击 | 数字 | 针对性 | 非适应性黑盒 | RML 2018.01A 自建数据集 | - |
| Yi等人[85] | 使用数据驱动的子采样策略,对未知子采样策略实现适应性黑盒攻击 | 数字 | 非针对性 | 白盒 | RML2016.10B | 48 (10) |
| 非针对性 | 适应性黑盒 | RML2016.10B | 70 (10) |
| Usama等人[86] | 实现白盒对抗攻击 | 数字 | 非针对性 | 白盒 | RML2016.10A | - |
| Usama等人[87] | 实现适应性黑盒对抗攻击 | 数字 | 非针对性 | 适应性黑盒 | RML2016.10A | 33 (10) |
| ATN | Flowers等人[29] | 利用扰动-对抗转化网络ARN实现对抗攻击,引入通信合页损失减少期望接收器误码率 | 物理 | 非针对性 | 白盒 | RML2016.10A (BPSK) | 25 (10) |
| DelVecchio等人[92] | 利用AMN实现对抗攻击,引入通信合页损失减少期望接收器误码率,并考虑前向纠错编码FEC影响 | 物理 | 非针对性 | 白盒 | 自建数据(QPSK) | 0 (10) |
| DelVecchio等人[93] | 改进AMN网络,考虑频谱欺骗损失,同时减少期望接收器的误码率 | 物理 | 非针对性 | 白盒 | 自建数据(QPSK) | 0 (10) |
| UAP | Sadeghi等人[16] | 利用主成分分析方法生成UAP | 数字 | 非针对性 | 适应性黑盒 | RML2016.10A | 37 (10) |
| Bahramali等人[25] | 构建扰动生成模型 PGM生成大量UAP,基于GAN构建噪声正则器,同时最大化UAP之间的距离 | 数字 | 非针对性 | 适应性黑盒 | RML2016.10A | 25 (10) |
| Kim等人[15,78] | 利用主成分分析和自编码器2种方法生成UAP,并考虑信道信息有限 | 数字 | 非针对性 | 适应性黑盒 | RML2016.10A | 46 (10) |
| 非针对性 | 严格黑盒 | RML2016.10A | 65 (10) |
| Sandler等人[96] | 生成UAP和特定类别的UAP,并添加随机相位偏移模拟真实信道 | 数字 | 非针对性 | 适应性黑盒 | RML 2018.01A, 自建数据集 | - |
| 针对性 | 适应性黑盒 | RML 2018.01A, 自建数据集 | - |
| BIM | Lin等人[20] | 比较多种方法性能,讨论波形变化 | 数字 | 非针对性 | 白盒 | RML2016.10A | 12 (10) |
| Sahay等人[88] | 基于频域特征分类,削弱非适应性黑盒对抗样本的可迁移性 | 数字 | 非针对性 | 白盒 | RML2016.10B | 20 (18) |
| 非针对性 | 非适应性黑盒 | RML2016.10B | 74 (18) |
| Lin等人[89] | 比较多种方法攻击性能,讨论调制类型鲁棒性 | 数字 | 非针对性 | 白盒 | RML2016.10A | 10 (10) |
| JSMA | Lin等人[89] | 基于JSMA方法实现严格黑盒攻击 | 数字 | 非针对性 | 严格黑盒 | RML2016.10A | 25 (10) |
| 木马攻击 | Davaslioglu等人[83] | 在一部分训练数据集中嵌入木马,在测试时触发木马以欺骗分类器 | 数字 | 针对性 | 白盒 | RML2016.10A | 攻击成功率 88 (12) |
), ArticleFig(id=1327013223917794092, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, label=表6, caption=
面向调制识别的对抗样本生成方法总览
, figureFileSmall=null, figureFileBig=null, tableContent=
| 攻击方法 | 相关研究工作 | 关键技术 | 攻击分类 | 攻击目标 | 攻击能力 | 数据集 | 攻击后最低准确率/ %(SNR/dB) |
|---|
| 注:“-”为当前文献未给出较为明确的攻击后最低准确率. |
| FGM | Sadeghi等人[16] | 使用二分法改进FGM | 数字 | 非针对性 | 白盒 | RML2016.10A | 0 (10) |
| Kim等人[15,78] | 最大接收扰动功率算法MRPP改进FGM | 数字 | 针对性 | 白盒 | RML2016.10A | 13 (10) |
| 非针对性 | 白盒 | RML2016.10A | 17 (10) |
| Restuccia等人[79] | 在一组连续的输入信号切片上计算扰动 | 数字 | 针对性 | 白盒 | RML 2018.01A | - |
| 非针对性 | 白盒 | RML 2018.01A | 31 (0) |
| Kokalj-Filipovic[26] | 通过自编码器对调制识别模型进行预训练,提高模型鲁棒性 | 数字 | 非针对性 | 非适应性黑盒 | RML 2018.01A (BPSK, QPSK, 9-PSK) | 60 (14) |
| Ke等人[82] | FGSM和L-BFGS对抗攻击 | 数字 | 非针对性 | 白盒 | RML2016.04C | 21 (8) |
| Lin等人[20] | 比较多种方法性能,讨论波形变化 | 数字 | 非针对性 | 白盒 | RML2016.10A | 17 (10) |
| Kim等人[84] | 采用元素最大信道增益EMCG法来优化天线信号功率分配,生成并发对抗性扰动 | 数字 | 针对性 | 白盒 | RML2016.10A | 10 (10) |
| Sahay等人[88] | 基于频域特征分类,削弱非适应性黑盒对抗样本的可迁移性 | 数字 | 非针对性 | 白盒 | RML2016.10B | 23 (18) |
| 非针对性 | 非适应性黑盒 | RML2016.10B | 78 (18) |
| Lin等人[89] | 比较多种方法攻击性能,讨论调制类型鲁棒性 | 数字 | 非针对性 | 白盒 | RML2016.10A | 14 (10) |
| Flowers等人[19] | FGSM实现对抗攻击,并考虑接收器误码率 | 物理 | 非针对性 | 白盒 | RML2016.10A (BPSK) | 58 (10) |
| Berian等人[95] | 基于滤波器方法实现对抗攻击 | 物理 | 非针对性 | 白盒 | RML2016.10A | 25 (0) |
| MI-FGSM | Bair等人[80] | 利用MI-FGSM实现针对性(QPSK被误分为8PSK)与非针对性对抗攻击 | 数字 | 针对性 | 白盒 | RML2016.10A | 0 (18) |
| 非针对性 | 白盒 | RML2016.10A | 7 (18) |
| Lin等人[20] | 比较多种方法性能,讨论波形变化 | 数字 | 非针对性 | 白盒 | RML2016.10A | 10 (10) |
| Lin等人[89] | 比较多种方法攻击性能,讨论调制类型鲁棒性 | 数字 | 非针对性 | 白盒 | RML2016.10A | 10 (10) |
| PGD | Lin等人[20] | 比较多种方法性能,讨论波形变化 | 数字 | 非针对性 | 白盒 | RML2016.10A | 13 (10) |
| Lin等人[89] | 比较多种方法攻击性能,讨论调制类型鲁棒性 | 数字 | 非针对性 | 白盒 | RML2016.10A | 13 (10) |
| Sandler等人[96] | 利用PGD方法实现对抗攻击 | 数字 | 非针对性 | 白盒 | RML 2018.01A, 自建数据集 | - |
| Hameed等人[90] | PGD方法实现对抗攻击,考虑接收器误码率的影响,将l2范数随机噪声作为对照组 | 物理 | 非针对性 | 白盒 | 自建数据(QAM64) | 55 (10) |
| 非针对性 | 非适应性黑盒 | 自建数据(QAM64) | 55 (10) |
| Hameed等人[91] | 改进PGD方法,并通过降低传输速率来权衡误码率与分类精度 | 物理 | 非针对性 | 白盒 | 自建数据(QAM64) | 55 (10) |
| 非针对性 | 非适应性黑盒 | 自建数据(QAM64) | 72 (10) |
| Hameed [94] | 改进PGD方法,考虑误码率的优化 | 物理 | 非针对性 | 白盒 | 自建数据(QAM64) | 55 (10) |
| 非针对性 | 非适应性黑盒 | 自建数据(QAM64) | 72 (10) |
| Carlini & Wagner | Kokalj-Filipovic等人[81] | 改进Carlini&Wagner-l2方法以适应调制识别对抗攻击 | 数字 | 针对性 | 非适应性黑盒 | RML 2018.01A 自建数据集 | - |
| Yi等人[85] | 使用数据驱动的子采样策略,对未知子采样策略实现适应性黑盒攻击 | 数字 | 非针对性 | 白盒 | RML2016.10B | 48 (10) |
| 非针对性 | 适应性黑盒 | RML2016.10B | 70 (10) |
| Usama等人[86] | 实现白盒对抗攻击 | 数字 | 非针对性 | 白盒 | RML2016.10A | - |
| Usama等人[87] | 实现适应性黑盒对抗攻击 | 数字 | 非针对性 | 适应性黑盒 | RML2016.10A | 33 (10) |
| ATN | Flowers等人[29] | 利用扰动-对抗转化网络ARN实现对抗攻击,引入通信合页损失减少期望接收器误码率 | 物理 | 非针对性 | 白盒 | RML2016.10A (BPSK) | 25 (10) |
| DelVecchio等人[92] | 利用AMN实现对抗攻击,引入通信合页损失减少期望接收器误码率,并考虑前向纠错编码FEC影响 | 物理 | 非针对性 | 白盒 | 自建数据(QPSK) | 0 (10) |
| DelVecchio等人[93] | 改进AMN网络,考虑频谱欺骗损失,同时减少期望接收器的误码率 | 物理 | 非针对性 | 白盒 | 自建数据(QPSK) | 0 (10) |
| UAP | Sadeghi等人[16] | 利用主成分分析方法生成UAP | 数字 | 非针对性 | 适应性黑盒 | RML2016.10A | 37 (10) |
| Bahramali等人[25] | 构建扰动生成模型 PGM生成大量UAP,基于GAN构建噪声正则器,同时最大化UAP之间的距离 | 数字 | 非针对性 | 适应性黑盒 | RML2016.10A | 25 (10) |
| Kim等人[15,78] | 利用主成分分析和自编码器2种方法生成UAP,并考虑信道信息有限 | 数字 | 非针对性 | 适应性黑盒 | RML2016.10A | 46 (10) |
| 非针对性 | 严格黑盒 | RML2016.10A | 65 (10) |
| Sandler等人[96] | 生成UAP和特定类别的UAP,并添加随机相位偏移模拟真实信道 | 数字 | 非针对性 | 适应性黑盒 | RML 2018.01A, 自建数据集 | - |
| 针对性 | 适应性黑盒 | RML 2018.01A, 自建数据集 | - |
| BIM | Lin等人[20] | 比较多种方法性能,讨论波形变化 | 数字 | 非针对性 | 白盒 | RML2016.10A | 12 (10) |
| Sahay等人[88] | 基于频域特征分类,削弱非适应性黑盒对抗样本的可迁移性 | 数字 | 非针对性 | 白盒 | RML2016.10B | 20 (18) |
| 非针对性 | 非适应性黑盒 | RML2016.10B | 74 (18) |
| Lin等人[89] | 比较多种方法攻击性能,讨论调制类型鲁棒性 | 数字 | 非针对性 | 白盒 | RML2016.10A | 10 (10) |
| JSMA | Lin等人[89] | 基于JSMA方法实现严格黑盒攻击 | 数字 | 非针对性 | 严格黑盒 | RML2016.10A | 25 (10) |
| 木马攻击 | Davaslioglu等人[83] | 在一部分训练数据集中嵌入木马,在测试时触发木马以欺骗分类器 | 数字 | 针对性 | 白盒 | RML2016.10A | 攻击成功率 88 (12) |
), ArticleFig(id=1327013224043623213, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, label=Table 7, caption=
Summary of Adversarial Attack Methods Considering Wireless Communication Characteristics, figureFileSmall=null, figureFileBig=null, tableContent=
| 通信特性 | 相关研究工作 | 处理方法 |
|---|
| 信道效应的复杂性 | 场景1: 不考虑模拟信道模型 | Sadeghi等人[16] | UAP具有移位不变性 |
| Bahramali等人[25] | UAP中添加相位旋转 |
场景1: 完整信道 模型 | Kim等人[15,78,95] | 利用信道效应改进对抗算法 |
| Kim等人[84] | 利用信道效应改进对抗算法,并合理分配多天线信号功率 |
| Flowers等人[19] | 提出特定信道与动态信道场景 实验 |
场景1: 有限信道 模型 | Flowers等人[29] | 引入通信合页损失 |
| Kim等人[15,78] | 采用PCA方法对信道信息降维,生成UAP |
| Restuccia等人[79] | 在一组连续的输入信号切片上计算扰动 |
| Sandler等人[96] | 真实信道上使用SDR广播对抗性扰动信号 |
| Flowers等人[19] | 提出特定信道与动态信道场景的实验 |
场景1: 物理对抗 攻击中利 用信道 差异 | Flowers等人[29] | 利用ATN的变体ARN进行对抗攻击 |
DelVecchio 等人[92-93] | 利用ATN的变体AMN进行对抗攻击 |
| Restuccia等人[90,94] | 基于DNN模型以多目标的线性组合为目标函数 |
| Hameed等人[91] | 多目标优化,并降低传输速率来权衡误码率与分类精度 |
场景2: 训练数据 集不同 | Sadeghi等 人[15-16,25,78,96] | 生成与输人无关的UAP |
特征表示的 异质性 | Lin等人[20] | 保证对抗攻击前后信号波形的一致,同时不减弱攻击性能 |
DelVecchio 等人[93] | 引入频谱欺骗损失,保持对抗性扰动信号的频谱完整性 |
| Sahay等人[88] | 基于频域特征分类,削弱黑盒对抗样本的可迁移性 |
信号数据的 间接性 | Flowers等 人[15,19,29,78-79,91-93] | 模拟信道模型,讨论分析前向纠错编码FEC等影响 |
), ArticleFig(id=1327013224140092206, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, label=表7, caption=
针对于无线通信特性的对抗攻击方法汇总
, figureFileSmall=null, figureFileBig=null, tableContent=
| 通信特性 | 相关研究工作 | 处理方法 |
|---|
| 信道效应的复杂性 | 场景1: 不考虑模拟信道模型 | Sadeghi等人[16] | UAP具有移位不变性 |
| Bahramali等人[25] | UAP中添加相位旋转 |
场景1: 完整信道 模型 | Kim等人[15,78,95] | 利用信道效应改进对抗算法 |
| Kim等人[84] | 利用信道效应改进对抗算法,并合理分配多天线信号功率 |
| Flowers等人[19] | 提出特定信道与动态信道场景 实验 |
场景1: 有限信道 模型 | Flowers等人[29] | 引入通信合页损失 |
| Kim等人[15,78] | 采用PCA方法对信道信息降维,生成UAP |
| Restuccia等人[79] | 在一组连续的输入信号切片上计算扰动 |
| Sandler等人[96] | 真实信道上使用SDR广播对抗性扰动信号 |
| Flowers等人[19] | 提出特定信道与动态信道场景的实验 |
场景1: 物理对抗 攻击中利 用信道 差异 | Flowers等人[29] | 利用ATN的变体ARN进行对抗攻击 |
DelVecchio 等人[92-93] | 利用ATN的变体AMN进行对抗攻击 |
| Restuccia等人[90,94] | 基于DNN模型以多目标的线性组合为目标函数 |
| Hameed等人[91] | 多目标优化,并降低传输速率来权衡误码率与分类精度 |
场景2: 训练数据 集不同 | Sadeghi等 人[15-16,25,78,96] | 生成与输人无关的UAP |
特征表示的 异质性 | Lin等人[20] | 保证对抗攻击前后信号波形的一致,同时不减弱攻击性能 |
DelVecchio 等人[93] | 引入频谱欺骗损失,保持对抗性扰动信号的频谱完整性 |
| Sahay等人[88] | 基于频域特征分类,削弱黑盒对抗样本的可迁移性 |
信号数据的 间接性 | Flowers等 人[15,19,29,78-79,91-93] | 模拟信道模型,讨论分析前向纠错编码FEC等影响 |
), ArticleFig(id=1327013225801036592, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, label=Table 8, caption=
Summary of Related Terms of Three Communication Characteristics on Adversarial Attack Research for Modulation Recognition, figureFileSmall=null, figureFileBig=null, tableContent=
| 相关研究工作 | 信道效应的 复杂性 | 信号数据的 间接性 | 特征表示的 异质性 |
|---|
| Kim等人[15] | ✓ | ✓ | |
| Sadeghi等人[16] | ✓ | | |
| Flowers等人[19] | ✓ | ✓ | |
| Lin等人[20] | | | ✓ |
| Bahramali等人[25] | ✓ | | |
| Kokalj-Filipovic等人[26] | | | |
| Flowers等人[29] | ✓ | ✓ | |
| Kim等人[78] | ✓ | ✓ | |
| Restuccia等人[79] | ✓ | ✓ | |
| Bair等人[80] | | | |
| Kokalj-Filipovic等人[81] | | | |
| Ke等人[82] | | | |
| Davaslioglu等人[83] | | | |
| Kim等人[84] | | | |
| Yi等人[85] | | | |
| Usama等人[86] | | | |
| Usama等人[87] | | | |
| Sahay等人[88] | | | ✓ |
| Lin等人[89] | | | |
| Hameed等人[90] | ✓ | ✓ | |
| Hameed等人[91] | ✓ | ✓ | |
| DelVecchio等人[92] | ✓ | ✓ | |
| DelVecchio等人[93] | ✓ | ✓ | ✓ |
| Hameed [94] | ✓ | ✓ | |
| Berian等人[95] | ✓ | ✓ | |
| Sandler等人[96] | ✓ | ✓ | |
), ArticleFig(id=1327013225918477105, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, label=表8, caption=
调制识别的对抗攻击研究工作对3种通信特性涉及项汇总
, figureFileSmall=null, figureFileBig=null, tableContent=
| 相关研究工作 | 信道效应的 复杂性 | 信号数据的 间接性 | 特征表示的 异质性 |
|---|
| Kim等人[15] | ✓ | ✓ | |
| Sadeghi等人[16] | ✓ | | |
| Flowers等人[19] | ✓ | ✓ | |
| Lin等人[20] | | | ✓ |
| Bahramali等人[25] | ✓ | | |
| Kokalj-Filipovic等人[26] | | | |
| Flowers等人[29] | ✓ | ✓ | |
| Kim等人[78] | ✓ | ✓ | |
| Restuccia等人[79] | ✓ | ✓ | |
| Bair等人[80] | | | |
| Kokalj-Filipovic等人[81] | | | |
| Ke等人[82] | | | |
| Davaslioglu等人[83] | | | |
| Kim等人[84] | | | |
| Yi等人[85] | | | |
| Usama等人[86] | | | |
| Usama等人[87] | | | |
| Sahay等人[88] | | | ✓ |
| Lin等人[89] | | | |
| Hameed等人[90] | ✓ | ✓ | |
| Hameed等人[91] | ✓ | ✓ | |
| DelVecchio等人[92] | ✓ | ✓ | |
| DelVecchio等人[93] | ✓ | ✓ | ✓ |
| Hameed [94] | ✓ | ✓ | |
| Berian等人[95] | ✓ | ✓ | |
| Sandler等人[96] | ✓ | ✓ | |
), ArticleFig(id=1327013226077860658, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=EN, label=Table 9, caption=
Comparison of Adversarial Defense and Detection Methods for Modulation Recognition, figureFileSmall=null, figureFileBig=null, tableContent=
| 类别 | 方法 | 详细技术 | 主要思想 | 优点 | 缺点 |
|---|
| 防御 | 对抗训练 | UAP对抗训练[25] | 最大化对抗损失、最小化模型参数损失,实现对抗信号防御 | 提升模型鲁棒性,操作相对容易 | 对训练数据与攻击方法具有依赖性,容易出现过拟合现象 |
| 自编码器预训练[26] |
| PGD对抗训练[91] |
| 随机平滑 | 基于随机平滑的可验证防御[15,25] | 通过高斯噪声对训练集进行数据增强,以提高分类器模型对多个梯度方向的鲁棒性 | 提升模型的泛化能力,对C&W攻击比其他防御机制的防御效果好 | 训练时间较长 |
| 降低噪声 | 扰动减法[25] | 根据对攻击者的了解程度,对受到扰动的接收信号进行信号处理,以消除扰动信号的影响 | 降低扰动影响,减小攻击成功率 | 需要扰动信号先验知识,防御效果较差 |
| 纠错编码 [91] | 提高编码效率 | 降低扰动影响,提升信息传输速率 | 防御效果较差 |
| 通信特性 | 利用信号特征 的异质性 [88] | 提出基于频域特征的信号调制识别模型,以抵御攻击者通过时域特征训练的代理模型发起的对抗攻击 | 频域特征训练的模型识别性能优于时域,并且对抗攻击防御效果较为优秀 | 依赖于信号数据集的特征表示形式 |
| 检测 | 统计学方法 | PAPR[27] | 利用接收信号的数字化射频样本数据的 PAPR进行统计测试 | 对抗检测精度较高 | 依赖于收集的输入样本的数量 |
| Softmax输出[27] | 利用DNNs模型最后一层的统计数据来检测由对抗样本引起的分布变化 | 对抗检测精度较高 | 依赖于信号波形和信道模型的影响 |
| 对抗触发器检测[83] | 利用MAD算法和聚类算法等统计学方法对触发器进行检测 | 对抗检测精度较高 | 依赖于训练数据集被投毒样本的数量 |
), ArticleFig(id=1327013226174329651, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013201381798566, language=CN, label=表9, caption=
面向调制识别的对抗防御与检测方法比较
, figureFileSmall=null, figureFileBig=null, tableContent=
| 类别 | 方法 | 详细技术 | 主要思想 | 优点 | 缺点 |
|---|
| 防御 | 对抗训练 | UAP对抗训练[25] | 最大化对抗损失、最小化模型参数损失,实现对抗信号防御 | 提升模型鲁棒性,操作相对容易 | 对训练数据与攻击方法具有依赖性,容易出现过拟合现象 |
| 自编码器预训练[26] |
| PGD对抗训练[91] |
| 随机平滑 | 基于随机平滑的可验证防御[15,25] | 通过高斯噪声对训练集进行数据增强,以提高分类器模型对多个梯度方向的鲁棒性 | 提升模型的泛化能力,对C&W攻击比其他防御机制的防御效果好 | 训练时间较长 |
| 降低噪声 | 扰动减法[25] | 根据对攻击者的了解程度,对受到扰动的接收信号进行信号处理,以消除扰动信号的影响 | 降低扰动影响,减小攻击成功率 | 需要扰动信号先验知识,防御效果较差 |
| 纠错编码 [91] | 提高编码效率 | 降低扰动影响,提升信息传输速率 | 防御效果较差 |
| 通信特性 | 利用信号特征 的异质性 [88] | 提出基于频域特征的信号调制识别模型,以抵御攻击者通过时域特征训练的代理模型发起的对抗攻击 | 频域特征训练的模型识别性能优于时域,并且对抗攻击防御效果较为优秀 | 依赖于信号数据集的特征表示形式 |
| 检测 | 统计学方法 | PAPR[27] | 利用接收信号的数字化射频样本数据的 PAPR进行统计测试 | 对抗检测精度较高 | 依赖于收集的输入样本的数量 |
| Softmax输出[27] | 利用DNNs模型最后一层的统计数据来检测由对抗样本引起的分布变化 | 对抗检测精度较高 | 依赖于信号波形和信道模型的影响 |
| 对抗触发器检测[83] | 利用MAD算法和聚类算法等统计学方法对触发器进行检测 | 对抗检测精度较高 | 依赖于训练数据集被投毒样本的数量 |
)], 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/issn1000-1239.202330826, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202330826, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202330826, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202330826, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1751299200000, fullTextJson=null, articleText=null, reference=null)