Adversarial Robustness On Cifar 100
Metrics
AutoAttacked Accuracy
Clean Accuracy
Results
Performance results of various models on this benchmark
Model Name | AutoAttacked Accuracy | Clean Accuracy | Paper Title | Repository |
|---|---|---|---|---|
| Mixed Classifier | 38.72 | 85.21 | Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing | |
| ResNet18/MART-ANCRA | 35.05 | 60.10 | Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria |
0 of 2 row(s) selected.