Generating adversarial examples without specifying a target model

PeerJ Computer Science

Ji Zhang¹  Gaoming Yang²  Xingzhu Liang²  Mingwei Li²  Xianjing Fang² 

[1] Department of Mathematics and Computing, University of Southern Queensland, Queensland, Australia;School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, China;

关键词: Deep learning;    Adversarial example;    Generative adversarial networks;    Adversarial machine learning;   

DOI  :  10.7717/peerj-cs.702

来源: DOAJ

【 摘 要 】

Adversarial examples are regarded as a security threat to deep learning models, and there are many ways to generate them. However, most existing methods require the query authority of the target during their work. In a more practical situation, the attacker will be easily detected because of too many queries, and this problem is especially obvious under the black-box setting. To solve the problem, we propose the Attack Without a Target Model (AWTM). Our algorithm does not specify any target model in generating adversarial examples, so it does not need to query the target. Experimental results show that it achieved a maximum attack success rate of 81.78% in the MNIST data set and 87.99% in the CIFAR-10 data set. In addition, it has a low time cost because it is a GAN-based method.

【 授权许可】

Unknown