Table 4 Test accuracies showing the impact of adversarial training, clean refers to the original testing data, FGSM refers to adversary examples derived from Fast Gradient Sign Method and PGD refers to adversarial examples derived from Projected Gradient Descent [83]
Models | MNIST | CIFAR-10 | ||||
|---|---|---|---|---|---|---|
Clean | FGSM | PGD | Clean | FGSM | PGD | |
Standard | 0.9939 | 0.0922 | 0 | 0.9306 | 0.5524 | 0.0256 |
Adversarially trained | 0.9932 | 0.9492 | 0.0612 | 0.8755 | 0.8526 | 0.1043 |
Our method | 0.9903 | 0.9713 | 0.9171 | 0.8714 | 0.6514 | 0.3440 |