Adversarial Defense On Cifar 10
평가 지표
Accuracy
Robust Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Accuracy | Robust Accuracy |
|---|---|---|
| robust-classification-via-a-single-diffusion | 89.85 | 75.67 |
| stochastic-local-winner-takes-all-networks | 81.87 | - |
| stochastic-local-winner-takes-all-networks | 84.3 | - |
| stochastic-local-winner-takes-all-networks | 83.4 | - |
| robust-representation-learning-via-asymmetric | 81.70 | 82.96 |
| adversarial-defense-by-restricting-the-hidden | 46.7 | - |
| language-guided-adversarial-purification | 90.03 | 71.68 |
| stochastic-local-winner-takes-all-networks | - | - |