A survey of robust adversarial training in pattern recognition: Fundamental, theory, and methodologies

doi:10.1016/j.patcog.2022.108889

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

	A survey of robust adversarial training in pattern recognition: Fundamental, theory, and methodologies
	Qian, Zhuang 2; Huang, Kaizhu 3; Wang, Qiu-Feng 2; Zhang, Xu-Yao 1,4
刊名	PATTERN RECOGNITION
	2022-11-01
卷号	131 页码:11
关键词	Adversarial examples Adversarial training Robust learning
ISSN号	0031-3203
DOI	10.1016/j.patcog.2022.108889
通讯作者	Huang, Kaizhu(kaizhu.huang@dukekunshan.edu.cn) ; Wang, Qiu-Feng(qiufeng.wang@xjtlu.edu.cn)
英文摘要	Deep neural networks have achieved remarkable success in machine learning, computer vision, and pattern recognition in the last few decades. Recent studies, however, show that neural networks (both shallow and deep) may be easily fooled by certain imperceptibly perturbed input samples called adversarial examples. Such security vulnerability has resulted in a large body of research in recent years because real-world threats could be introduced due to the vast applications of neural networks. To address the robustness issue to adversarial examples particularly in pattern recognition, robust adversarial training has become one mainstream. Various ideas, methods, and applications have boomed in the field. Yet, a deep understanding of adversarial training including characteristics, interpretations, theories, and connections among different models has remained elusive. This paper presents a comprehensive survey trying to offer a systematic and structured investigation on robust adversarial training in pattern recognition. We start with fundamentals including definition, notations, and properties of adversarial examples. We then introduce a general theoretical framework with gradient regularization for defending against adversarial samples - robust adversarial training with visualizations and interpretations on why adversarial training can lead to model robustness. Connections will also be established between adversarial training and other traditional learning theories. After that, we summarize, review, and discuss various methodologies with defense/training algorithms in a structured way. Finally, we present analysis, outlook, and remarks on adversarial training. (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)[61876155] ; National Natural Science Foundation of China (NSFC)[61876154] ; Jiangsu Science and Technology Pro-gramme (Natural Science Foundation of Jiangsu Province)[BE2020006-4]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000854976600009
资助机构	National Key Research and Development Program ; National Natural Science Foundation of China (NSFC) ; Jiangsu Science and Technology Pro-gramme (Natural Science Foundation of Jiangsu Province)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/50134]
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	Huang, Kaizhu; Wang, Qiu-Feng
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 2.Xian Jiaotong Liverpool Univ, Sch Adv Technol, Suzhou, Peoples R China 3.Duke Kunshan Univ, Data Sci Res Ctr, Suzhou, Peoples R China 4.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Qian, Zhuang,Huang, Kaizhu,Wang, Qiu-Feng,et al. A survey of robust adversarial training in pattern recognition: Fundamental, theory, and methodologies[J]. PATTERN RECOGNITION,2022,131:11.
APA	Qian, Zhuang,Huang, Kaizhu,Wang, Qiu-Feng,&Zhang, Xu-Yao.(2022).A survey of robust adversarial training in pattern recognition: Fundamental, theory, and methodologies.PATTERN RECOGNITION,131,11.
MLA	Qian, Zhuang,et al."A survey of robust adversarial training in pattern recognition: Fundamental, theory, and methodologies".PATTERN RECOGNITION 131(2022):11.