Table 5 Classification accuracy on the CIFAR-10 test dataset under white-box attacks
From: Secure machine learning against adversarial samples at test time
Attack | FGSM | C&W | BIM | DeepFool |
|---|---|---|---|---|
Original | 16% | 46% | 8% | 13% |
Robust classifier | 47% | 78% | 80% | 36% |
From: Secure machine learning against adversarial samples at test time
Attack | FGSM | C&W | BIM | DeepFool |
|---|---|---|---|---|
Original | 16% | 46% | 8% | 13% |
Robust classifier | 47% | 78% | 80% | 36% |