Image Classification on CIFAR-10 (Adversarial Robustness)
56.83FGSM Accuracy (8/255)Zubov-Net
Evaluation results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Zubov-Net2025.09 | 56.83 | 53.77 | 59.94 | 59.37 | 75.01 | 67.74 | 58.03 | 57.81 | 44.87 | 37.78 | 57.12 | |
| FxTS-Net2025.09 | 49.79 | 48.18 | 56.36 | 55.86 | 71.65 | 65.41 | 54.2 | 54.06 | 31.81 | 22.14 | 50.95 | |
| LyaNet2025.09 | 49.3 | 48.08 | 55.23 | 55.16 | 71.49 | 66.37 | 53.08 | 52.37 | 30.28 | 20.55 | 50.19 | |
| SODEF2025.09 | 47.54 | 40.88 | 57.36 | 57.15 | 64.01 | 43.87 | 55.42 | 55.18 | 29.95 | 20.02 | 47.14 | |
| Proj-NODE2025.09 | 45.05 | 38.12 | 57.17 | 56.77 | 60.74 | 41.02 | 55.27 | 54.14 | 26.24 | 16.81 | 45.13 | |
| Neural ODE2025.09 | 40.95 | 32.37 | 52.79 | 52.23 | 62.55 | 41.38 | 50.01 | 49.97 | 18.32 | 7.02 | 40.76 | |
| ResNet182025.09 | 39.66 | 30.99 | 52.48 | 51.97 | 61.35 | 40.26 | 50.43 | 50.23 | 18.3 | 6.9 | 40.26 |