| Paper | Code | Accuracy | Robust Accuracy | Attack: AutoAttack | ModelName | ReleaseDate |
|---|---|---|---|---|---|---|
| Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing | ✓ Link | 95.23 | 68.06 | 68.06 | Mixed classifier | 2023-01-29 |
| Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness | ✓ Link | 92.26 | 84.3 | 82.6 | Stochastic-LWTA/PGD/WideResNet-34-10 | 2021-12-05 |
| Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness | ✓ Link | 91.88 | 83.4 | 81.22 | Stochastic-LWTA/PGD/WideResNet-34-5 | 2021-12-05 |
| Global-Local Regularization Via Distributional Robustness | ✓ Link | 84.13 | 49.94 | GLOT-DR | 2022-03-01 | |
| Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria | ✓ Link | 81.70 | 59.70 | TRADES-ANCRA/ResNet18 | 2023-10-05 |