Adversarial training with distribution normalization and margin balance

doi:10.1016/j.patcog.2022.109182

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 模式分析与学习

	Adversarial training with distribution normalization and margin balance
	Cheng, Zhen 1,2; Zhu, Fei 1,2; Zhang, Xu-Yao1,2 ; Liu, Cheng-Lin1,2
发表期刊	PATTERN RECOGNITION
ISSN	0031-3203
	2023-04-01
卷号	136 页码:11
通讯作者	Zhang, Xu-Yao(xyz@nlpr.ia.ac.cn)
摘要	Adversarial training is the most effective method to improve adversarial robustness. However, it does not explicitly regularize the feature space during training. Adversarial attacks usually move a sample it-eratively along the direction which causes the steepest ascent of classification loss by crossing decision boundary. To alleviate this problem, we propose to regularize the distributions of different classes to increase the difficulty of finding an attacking direction. Specifically, we propose two strategies named Distribution Normalization (DN) and Margin Balance (MB) for adversarial training. The purpose of DN is to normalize the features of each class to have identical variance in every direction, in order to elimi-nate easy-to-attack intra-class directions. The purpose of MB is to balance the margins between different classes, making it harder to find confusing class directions (i.e., those with smaller margins) to attack. When integrated with adversarial training, our method can significantly improve adversarial robustness. Extensive experiments under white-box, black-box, and adaptive attacks demonstrate the effectiveness of our method over other state-of-the-art methods.(c) 2022 Elsevier Ltd. All rights reserved.
关键词	Adversarial robustness Adversarial training Distribution normalization Margin balance
DOI	10.1016/j.patcog.2022.109182
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program[2018AAA0100400] ; National Natural Science Foundation of China (NSFC)[U20A20223] ; National Natural Science Foundation of China (NSFC)[62222609] ; National Natural Science Foundation of China (NSFC)[62076236] ; National Natural Science Foundation of China (NSFC)[61721004] ; Key Research Program of Frontier Sciences of Chinese Academy of Sciences[ZDBS-LY-7004] ; Youth Innovation Promotion Association of Chinese Academy of Sciences[2019141]
项目资助者	National Key Research and Development Program ; National Natural Science Foundation of China (NSFC) ; Key Research Program of Frontier Sciences of Chinese Academy of Sciences ; Youth Innovation Promotion Association of Chinese Academy of Sciences
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000891819300004
出版者	ELSEVIER SCI LTD
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/50828
专题	多模态人工智能系统全国重点实验室_模式分析与学习
通讯作者	Zhang, Xu-Yao
作者单位	1.Chinese Acad Sci, Natl Lab Pattern Recognit NLPR, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci UCAS, Sch Artificial Intelligence, Beijing 100049, Peoples R China
第一作者单位	模式识别国家重点实验室
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Cheng, Zhen,Zhu, Fei,Zhang, Xu-Yao,et al. Adversarial training with distribution normalization and margin balance[J]. PATTERN RECOGNITION,2023,136:11.
APA	Cheng, Zhen,Zhu, Fei,Zhang, Xu-Yao,&Liu, Cheng-Lin.(2023).Adversarial training with distribution normalization and margin balance.PATTERN RECOGNITION,136,11.
MLA	Cheng, Zhen,et al."Adversarial training with distribution normalization and margin balance".PATTERN RECOGNITION 136(2023):11.