Weiwei Liu, Boqi Li
We lifted 1 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| boqili/WAT | — | 0 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| TRADES_classwise_loss | Not yet run | boqili/WAT/worst_class_adversarial_train.py code served (permissive licence) · get_code("d5559ea960ed1ba8") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Deep Neural Networks (DNN) have been shown to be vulnerable to adversarial examples. Adversarial training (AT) is a popular and effective strategy to defend against adversarial attacks. Recent works have shown that a robust model well-trained by AT exhibits a remarkable robustness disparity among classes, and propose various methods to obtain consistent robust accuracy across classes. Unfortunately, these methods sacrifice a good deal of the average robust accuracy. Accordingly, this paper proposes a novel framework of worstclass adversarial training and leverages no-regret dynamics to solve this problem. Our goal is to obtain a classifier with great performance on worst-class and sacrifice just a little average robust accuracy at the same time. We then rigorously analyze the theoretical properties of our proposed algorithm, and the generalization error bound in terms of the worst-class robust risk. Furthermore, we propose a measurement to evaluate the proposed method in terms of both the average and worst-class accuracies. Experiments on various datasets and networks show that our proposed method outperforms the state-of-the-art approaches.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2302.04025")
get_code_for_paper("2302.04025")
have("2302.04025")
Connect an agent — have() is free.