Abstract | ||
---|---|---|
Deep neural networks are becoming increasingly popular. However, they are also vulnerable to adversarial attacks. The existing attack methods include white-box attack and black-box attack. The white-box attack assumes full model knowledge while the black-box one assumes none. In this brief, we propose a novel attack method between these two. Specifically, we have made the following contributions: (1) we propose the gray-box attack, which utilizes the side-channel attack to predict the model structure based on a pre-trained classifier and (2) we validate our method on real-world experiments. The experimental results show that our gray-box attack can significantly outperform the existing techniques. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/TCSII.2020.3012005 | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS |
Keywords | DocType | Volume |
Training, Predictive models, Perturbation methods, Jacobian matrices, Mathematical model, Circuits and systems, Deep neural network, side-channel attack, adversarial attack | Journal | 68 |
Issue | ISSN | Citations |
1 | 1549-7747 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yun Xiang | 1 | 164 | 9.23 |
Yongchao Xu | 2 | 0 | 0.34 |
Yingjie Li | 3 | 0 | 0.34 |
Wen Ma | 4 | 0 | 0.34 |
Qi Xuan | 5 | 187 | 26.85 |
Yi Liu | 6 | 10 | 6.01 |