Adversarial Perturbation Defense on Deep Neural Networks

doi:10.1145/3465397

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 互联网大数据与信息安全

	Adversarial Perturbation Defense on Deep Neural Networks
	Zhang, Xingwei; Zheng, Xiaolong; Mao, Wenji
发表期刊	ACM COMPUTING SURVEYS
ISSN	0360-0300
	2021-11-01
卷号	54 期号:8 页码:36
通讯作者	Zheng, Xiaolong(xiaolong.zheng@ia.ac.cn)
摘要	Deep neural networks (DNNs) have been verified to be easily attacked by well-designed adversarial perturbations. Image objects with small perturbations that are imperceptible to human eyes can induce DNN-based image class classifiers towards making erroneous predictions with high probability. Adversarial perturbations can also fool real-world machine learning systems and transfer between different architectures and datasets. Recently, defense methods against adversarial perturbations have become a hot topic and attracted much attention. A large number of works have been put forward to defend against adversarial perturbations, enhancing DNN robustness against potential attacks, or interpreting the origin of adversarial perturbations. In this article, we provide a comprehensive survey on classical and state-of-the-art defense methods by illuminating their main concepts, in-depth algorithms, and fundamental hypotheses regarding the origin of adversarial perturbations. In addition, we further discuss potential directions of this domain for future researchers.
关键词	Adversarial perturbation defense deep neural networks security origin
DOI	10.1145/3465397
关键词[WOS]	EVASION ATTACKS ; ROBUSTNESS
收录类别	SCI
语种	英语
资助项目	Ministry of Health of China[2017ZX10303401-002] ; Ministry of Health of China[2017YFC1200302] ; Ministry of Science and Technology of China[2020AAA0108401and 2019QY(Y)0101] ; Natural Science Foundation of China[71602184] ; Natural Science Foundation of China[71621002]
项目资助者	Ministry of Health of China ; Ministry of Science and Technology of China ; Natural Science Foundation of China
WOS研究方向	Computer Science
WOS类目	Computer Science, Theory & Methods
WOS记录号	WOS:000705073600003
出版者	ASSOC COMPUTING MACHINERY
七大方向——子方向分类	机器学习
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/46189
专题	多模态人工智能系统全国重点实验室_互联网大数据与信息安全
通讯作者	Zheng, Xiaolong
作者单位	Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Zhang, Xingwei,Zheng, Xiaolong,Mao, Wenji. Adversarial Perturbation Defense on Deep Neural Networks[J]. ACM COMPUTING SURVEYS,2021,54(8):36.
APA	Zhang, Xingwei,Zheng, Xiaolong,&Mao, Wenji.(2021).Adversarial Perturbation Defense on Deep Neural Networks.ACM COMPUTING SURVEYS,54(8),36.
MLA	Zhang, Xingwei,et al."Adversarial Perturbation Defense on Deep Neural Networks".ACM COMPUTING SURVEYS 54.8(2021):36.