Adversarial Attack On Cifar 10
评估指标
Attack: PGD20
评测结果
各个模型在此基准测试上的表现结果
模型名称 | Attack: PGD20 | Paper Title | Repository |
|---|---|---|---|
| TRADES [zhang2019b] | 45.900 | Theoretically Principled Trade-off between Robustness and Accuracy | |
| AdvTraining [madry2018] | 48.440 | Towards Deep Learning Models Resistant to Adversarial Attacks | |
| XU-Net | - | Attention Masks Help Adversarial Attacks to Bypass Safety Detectors | - |
| 3-ensemble of multi-resolution self-ensembles | - | Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness | |
| Xu et al. | 78.680 | An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networks | |
| TRADES-ANCRA/ResNet18 | - | Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria |
0 of 6 row(s) selected.