Moving target defense against adversarial attacks
Deep neural network has been successfully applied to image classification, but recent research work shows that deep neural network is vulnerable to adversarial attacks. A moving target defense method was proposed by means of dynamic switching model with a Bayes-Stackelberg game strategy, which could...
Main Authors: | WANG Bin, CHEN Liang, QIAN Yaguan, GUO Yankai, SHAO Qiqi, WANG Jiamin |
---|---|
Format: | Article |
Language: | English |
Published: |
POSTS&TELECOM PRESS Co., LTD
2021-02-01
|
Series: | 网络与信息安全学报 |
Subjects: | |
Online Access: | http://www.infocomm-journal.com/cjnis/CN/10.11959/j.issn.2096-109x.2021012 |
Similar Items
-
Adversarial attacks and defenses in deep learning
by: LIU Ximeng, et al.
Published: (2020-10-01) -
Adversarial Attack and Defense Strategies of Speaker Recognition Systems: A Survey
by: Hao Tan, et al.
Published: (2022-07-01) -
Survey of Image Adversarial Example Defense Techniques
by: LIU Ruiqi, LI Hu, WANG Dongxia, ZHAO Chongyang, LI Boyu
Published: (2023-12-01) -
Adversarial Attack and Defense on Deep Neural Network-Based Voice Processing Systems: An Overview
by: Xiaojiao Chen, et al.
Published: (2021-09-01) -
Adversarial attack and defense in reinforcement learning-from AI security view
by: Tong Chen, et al.
Published: (2019-03-01)