A Survey of Adversarial Examples in Computer Vision:Attack,Defense,and Beyond

作     者：XU Keyizhi LU Yajuan WANG Zhongyuan LIANG Chao 徐可易之;陆雅娟;王中元;梁超

作者机构：School of Computer ScienceWuhan UniversityWuhan 430072HubeiChina National Engineering Research Center for Multimedia Software(NERCMS)Wuhan UniversityWuhan 430072HubeiChina Key Laboratory of Multimedia and Network Communication EngineeringHubei ProvinceWuhan UniversityWuhan 430072HubeiChina School of Cyber Science and EngineeringWuhan UniversityWuhan 430072HubeiChina 

基　　金：Supported by the National Natural Science Foundation of China(U1903214,62372339,62371350,61876135) the Ministry of Education Industry University Cooperative Education Project(202102246004,220800006041043,202002142012) the Fundamental Research Funds for the Central Universities(2042023kf1033) 

出 版 物：《Wuhan University Journal of Natural Sciences》 (武汉大学学报(自然科学英文版))

年 卷 期：2025年第30卷第1期

页      码：1-20页

摘      要：Recent years have witnessed the ever-increasing performance of Deep Neural Networks(DNNs)in computer vision ***,researchers have identified a potential vulnerability:carefully crafted adversarial examples can easily mislead DNNs into incorrect behavior via the injection of imperceptible modification to the input *** this survey,we focus on(1)adversarial attack algorithms to generate adversarial examples,(2)adversarial defense techniques to secure DNNs against adversarial examples,and(3)important problems in the realm of adversarial examples beyond attack and defense,including the theoretical explanations,trade-off issues and benign attacks in adversarial ***,we draw a brief comparison between recently published surveys on adversarial examples,and identify the future directions for the research of adversarial examples,such as the generalization of methods and the understanding of transferability,that might be solutions to the open problems in this field.

主 题 词：computer vision adversarial examples adversarial attack adversarial defense 

学科分类：12[管理学] 1201[管理学-管理科学与工程类] 081104[081104] 08[工学] 0835[0835] 0811[工学-水利类] 0812[工学-测绘类] 

核心收录：

D　O　I：10.1051/wujns/2025301001

馆 藏 号：203157375...