GreedyFool: Distortion-Aware Sparse Adversarial Attack

Modern deep neural networks(DNNs) are vulnerable to adversarial samples. Sparse adversarial samples are a special branch of adversarial samples that can fool the target model by only perturbing a few pixels. The existence of the sparse adversarial attack points out that DNNs are much more vulnerable than people believed, which is also a new aspect for analyzing DNNs. However, current sparse adversarial attack methods still have some shortcomings on both sparsity and invisibility. In this paper, we propose a novel two-stage distortion-aware greedy-based method dubbed as ''GreedyFool". Specifically, it first selects the most effective candidate positions to modify by considering both the gradient(for adversary) and the distortion map(for invisibility), then drops some less important points in the reduce stage. Experiments demonstrate that compared with the start-of-the-art method, we only need to modify 3 times fewer pixels under the same sparse perturbation setting. For target attack, the success rate of our method is 9. 96% higher than the start-of-the-art method under the same pixel budget.

Authors

• Xiaoyi Dong Shanghai Artificial Intelligence Laboratory The Chinese University of Hong Kong
• DongDong Chen Microsoft Corporation
• Jianmin Bao Microsoft Research Asia
• Chuan Qin
• Lu Yuan Stanford University
• Weiming Zhang University of Science and Technology of China
• Nenghai Yu School of Cyber Science and Technology, University of Science and Technology of China Anhui Province Key Laboratory of Digital Security the CCCD Key Lab of Ministry of Culture and Tourism
• Dong Chen Zhejiang University

Keywords

No keywords are indexed for this paper.