中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 模式分析与学习团队
Adversarial training with distribution normalization and margin balance

文献类型：期刊论文

作者Cheng, Zhen1,2; Zhu, Fei1,2; Zhang, Xu-Yao1,2; Liu, Cheng-Lin1,2
刊名PATTERN RECOGNITION
出版日期2023-04-01
卷号136页码:11
ISSN号0031-3203
关键词Adversarial robustness Adversarial training Distribution normalization Margin balance
DOI10.1016/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
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.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。