Image Classification on CIFAR-10 (val) (Metrics: Acc, ASR, FGA)
87.8AccuracyFGA
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| FGAModel=VGG-19, Attack Type=BadNets, Poison Rate=10%2026.03 | 87.8 | 98.23 | 99.34 | |
| FGAModel=VGG-19, Attack Type=Blend, Poison Rate=10%2026.03 | 87.8 | 87.08 | 99.76 | |
| FGAModel=VGG-19, Attack Type=WaNet, Poison Rate=10%2026.03 | 87.8 | 63.8 | 99.99 | |
| FGAModel=VGG-19, Attack Type=Input-Aware, Poison Rate=10%2026.03 | 87.8 | 91.11 | 97.98 | |
| FGAModel=ResNet-18, Attack Type=BadNets, Poison Rate=10%2026.03 | 78.9 | 97.3 | 99.78 | |
| FGAModel=ResNet-18, Attack Type=Blend, Poison Rate=10%2026.03 | 78.9 | 83.98 | 99.53 | |
| FGAModel=ResNet-18, Attack Type=WaNet, Poison Rate=10%2026.03 | 78.9 | 60.29 | 100 | |
| FGAModel=ResNet-18, Attack Type=Input-Aware, Poison Rate=10%2026.03 | 78.9 | 88.32 | 92.36 |