Adversarial Defense On Imagenet Non Targeted
评估指标
Accuracy
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | Accuracy |
|---|---|
| adversarial-training-for-free | 36.0% |
| adversarial-training-for-free | 34.3% |
| adversarial-robustness-through-local | 47.0% |
| smooth-adversarial-training | 58.6% |
| adversarial-training-for-free | 31.8% |