Name
Abstract | ||
|---|---|---|
We propose a simple change to existing neural network structures for better defending against gradient-based adversarial attacks. Instead of using popular activation functions (such as ReLU), we advocate the use of k-Winners-Take-All (k-WTA) activation, a C0 discontinuous function that purposely invalidates the neural network model’s gradient at densely distributed input data points. The proposed k-WTA activation can be readily used in nearly all existing networks and training methods with no significant overhead. Our proposal is theoretically rationalized. We analyze why the discontinuities in k-WTA networks can largely prevent gradient-based search of adversarial examples and why they at the same time remain innocuous to the network training. This understanding is also empirically backed. We test k-WTA activation on various network structures optimized by a training method, be it adversarial training or not. In all cases, the robustness of k-WTA networks outperforms that of traditional networks under white-box attacks. |
Year | Venue | Keywords |
|---|---|---|
2020 | ICLR | adversarial defense, activation function, winner takes all |
DocType | Citations | PageRank |
Conference | 1 | 0.34 |
References | Authors | |
47 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chang Xiao | 1 | 11 | 4.00 |
| Peilin Zhong | 2 | 99 | 10.36 |
| Changxi Zheng | 3 | 571 | 37.17 |