Image Classification on CIFAR-10 (Noise Scale and Rate Analysis)
7,166Noise ScaleLaDP-FL
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| LaDP-FLepsilon=0.5, Model Architecture=CNN2026.01 | 7,166 | — | — | |
| Sensitive DPepsilon=0.5, Model Architecture=CNN2026.01 | 8,378 | 14.47 | — | |
| LaDP-FLepsilon=0.4, Model Architecture=CNN2026.01 | 8,798 | — | — | |
| DPAepsilon=0.5, Model Architecture=CNN2026.01 | 9,033 | 20.67 | — | |
| Sensitive DPepsilon=0.4, Model Architecture=CNN2026.01 | 9,047 | 2.75 | — | |
| Time-Varying DPepsilon=0.5, Model Architecture=CNN2026.01 | 11,549 | 37.94 | — | |
| DPAepsilon=0.4, Model Architecture=CNN2026.01 | 14,029 | 37.29 | — | |
| LaDP-FLepsilon=0.3, Model Architecture=CNN2026.01 | 15,870 | — | — | |
| Sensitive DPepsilon=0.3, Model Architecture=CNN2026.01 | 17,038 | 6.86 | — | |
| Time-Varying DPepsilon=0.4, Model Architecture=CNN2026.01 | 18,156 | 51.54 | — | |
| Full DPepsilon=0.5, Model Architecture=CNN2026.01 | 19,852 | 63.9 | — | |
| LDPepsilon=0.5, Model Architecture=CNN2026.01 | 20,149 | 64.43 | — | |
| LaDP-FLepsilon=0.2, Model Architecture=CNN2026.01 | 21,747 | — | — | |
| Sensitive DPepsilon=0.2, Model Architecture=CNN2026.01 | 22,754 | 4.43 | 7.12 | |
| DPAepsilon=0.3, Model Architecture=CNN2026.01 | 24,647 | 35.61 | — | |
| Time-Varying DPepsilon=0.3, Model Architecture=CNN2026.01 | 30,983 | 48.78 | — | |
| DPAepsilon=0.2, Model Architecture=CNN2026.01 | 31,052 | 29.97 | 30.88 | |
| Full DPepsilon=0.4, Model Architecture=CNN2026.01 | 34,717 | 74.66 | — | |
| LDPepsilon=0.4, Model Architecture=CNN2026.01 | 36,140 | 75.66 | — | |
| Time-Varying DPepsilon=0.2, Model Architecture=CNN2026.01 | 44,752 | 51.41 | 47.42 | |
| LDPepsilon=0.3, Model Architecture=CNN2026.01 | 45,913 | 65.43 | — | |
| Full DPepsilon=0.3, Model Architecture=CNN2026.01 | 48,236 | 67.1 | — | |
| LaDP-FLepsilon=0.5, Model Architecture=ResNet-182026.01 | 51,658 | — | — | |
| Sensitive DPepsilon=0.5, Model Architecture=ResNet-182026.01 | 53,997 | 4.33 | — | |
| Full DPepsilon=0.2, Model Architecture=CNN2026.01 | 61,523 | 64.65 | 67.58 | |
| LDPepsilon=0.2, Model Architecture=CNN2026.01 | 63,489 | 65.75 | 67.82 | |
| LaDP-FLepsilon=0.4, Model Architecture=ResNet-182026.01 | 87,563 | — | — | |
| Sensitive DPepsilon=0.4, Model Architecture=ResNet-182026.01 | 95,468 | 8.28 | — | |
| LaDP-FLepsilon=0.3, Model Architecture=ResNet-182026.01 | 132,365 | — | — | |
| DPAepsilon=0.5, Model Architecture=ResNet-182026.01 | 156,947 | 67.09 | — | |
| Sensitive DPepsilon=0.3, Model Architecture=ResNet-182026.01 | 165,234 | 19.89 | — | |
| Time-Varying DPepsilon=0.5, Model Architecture=ResNet-182026.01 | 193,487 | 73.3 | — | |
| Full DPepsilon=0.5, Model Architecture=ResNet-182026.01 | 203,968 | 74.67 | — | |
| LDPepsilon=0.5, Model Architecture=ResNet-182026.01 | 217,344 | 76.23 | — | |
| Time-Varying DPepsilon=0.4, Model Architecture=ResNet-182026.01 | 224,129 | 60.93 | — | |
| DPAepsilon=0.4, Model Architecture=ResNet-182026.01 | 241,778 | 63.78 | — | |
| Sensitive DPepsilon=0.2, Model Architecture=ResNet-182026.01 | 242,583 | -13.55 | 4.74 | |
| DPAepsilon=0.3, Model Architecture=ResNet-182026.01 | 261,698 | 49.42 | — | |
| LaDP-FLepsilon=0.2, Model Architecture=ResNet-182026.01 | 275,447 | — | — | |
| Time-Varying DPepsilon=0.3, Model Architecture=ResNet-182026.01 | 295,231 | 55.17 | — | |
| Full DPepsilon=0.4, Model Architecture=ResNet-182026.01 | 383,945 | 77.19 | — | |
| DPAepsilon=0.2, Model Architecture=ResNet-182026.01 | 386,453 | 28.72 | 52.25 | |
| LDPepsilon=0.4, Model Architecture=ResNet-182026.01 | 402,970 | 78.27 | — | |
| Full DPepsilon=0.3, Model Architecture=ResNet-182026.01 | 505,266 | 73.8 | — | |
| LDPepsilon=0.3, Model Architecture=ResNet-182026.01 | 512,366 | 74.17 | — | |
| Full DPepsilon=0.2, Model Architecture=ResNet-182026.01 | 727,901 | 62.16 | 71.96 | |
| LDPepsilon=0.2, Model Architecture=ResNet-182026.01 | 735,138 | 62.53 | 72.8 | |
| Time-Varying DPepsilon=0.2, Model Architecture=ResNet-182026.01 | 862,998 | 68.08 | 64.37 |