GCSA: A New Adversarial Example-Generating Scheme Toward Black-Box Adversarial Attacks

doi:10.1109/TCE.2024.3358179

	GCSA: A New Adversarial Example-Generating Scheme Toward Black-Box Adversarial Attacks
	Fan, Xinxin 1; Li, Mengfan 1; Zhou, Jia 2; Jing, Quanliang 1; Lin, Chi 3; Lu, Yunfeng 4; Bi, Jingping 1
	2024-02-01
发表期刊	IEEE TRANSACTIONS ON CONSUMER ELECTRONICS
ISSN	0098-3063
卷号	70 期号:1 页码:2038-2048
摘要	This paper focuses on the transferability problem of adversarial examples towards black-box attack scenarios wherein model information such as the neural network structure is unavailable. To tackle this predicament, we propose a new adversarial example-generating scheme through bridging a data-modal conversion regime to spawn transferable adversarial examples without referring to the substitute model. Three contributions are mainly involved: i) we figure out an integrated framework to produce transferable adversarial examples through resorting to three components, i.e., image-to-graph conversion, perturbation on converted graph and graph-to-image inversion; ii) upon the conversion from image to graph, we pinpoint critical graph characteristics to implement perturbation using gradient-oriented and optimization-oriented adversarial attacks, then, invert the perturbation on graph into the pixel disturbance correspondingly; iii) multi-facet experiments verify the reasonability and effectiveness with the comparison to three baseline methods. Our work has two novelties: first, without referring to the substitute model, our proposed scheme does not need to acquire any information about the victim model in advance; second, we explore the possibility that inferring the adversarial features of image data through drawing support from network/graph science. In addition, we present three key issues worth deeper discussion, along with these open issues, our work deserves more studies in future.
关键词	Closed box Perturbation methods Predictive models Indexes Training Glass box Optimization Deep learning adversarial examples black-box adversarial attack transferability
DOI	10.1109/TCE.2024.3358179
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China
WOS研究方向	Engineering ; Telecommunications
WOS类目	Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:001244821700068
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/39913
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Fan, Xinxin
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.Bank Commun, Shanghai 200120, Peoples R China 3.Dalian Univ Technol, Sch Software Technol, Dalian 116024, Peoples R China 4.Beihang Univ, Sch Reliabil & Syst, Beijing 100191, Peoples R China
推荐引用方式 GB/T 7714	Fan, Xinxin,Li, Mengfan,Zhou, Jia,et al. GCSA: A New Adversarial Example-Generating Scheme Toward Black-Box Adversarial Attacks[J]. IEEE TRANSACTIONS ON CONSUMER ELECTRONICS,2024,70(1):2038-2048.
APA	Fan, Xinxin.,Li, Mengfan.,Zhou, Jia.,Jing, Quanliang.,Lin, Chi.,...&Bi, Jingping.(2024).GCSA: A New Adversarial Example-Generating Scheme Toward Black-Box Adversarial Attacks.IEEE TRANSACTIONS ON CONSUMER ELECTRONICS,70(1),2038-2048.
MLA	Fan, Xinxin,et al."GCSA: A New Adversarial Example-Generating Scheme Toward Black-Box Adversarial Attacks".IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 70.1(2024):2038-2048.