Adversarial training with distribution normalization and margin balance

doi:10.1016/j.patcog.2022.109182

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 模式分析与学习团队

	Adversarial training with distribution normalization and margin balance
	Cheng, Zhen 1,2; Zhu, Fei 1,2; Zhang, Xu-Yao 1,2; Liu, Cheng-Lin 1,2
刊名	PATTERN RECOGNITION
	2023-04-01
卷号	136 页码:11
关键词	Adversarial robustness Adversarial training Distribution normalization Margin balance
ISSN号	0031-3203
DOI	10.1016/j.patcog.2022.109182
通讯作者	Zhang, Xu-Yao(xyz@nlpr.ia.ac.cn)
英文摘要	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.
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]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000891819300004
资助机构	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
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/50827]
专题	自动化研究所_模式识别国家重点实验室_模式分析与学习团队
通讯作者	Zhang, Xu-Yao
作者单位	1.Univ Chinese Acad Sci UCAS, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Natl Lab Pattern Recognit NLPR, Inst Automat, Beijing 100190, Peoples R China
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.