In fact, your SR is 99% only in the case of untargeted attack

[Sunshine352]

No description provided.

[mathcbc]

the accuracy of the targeted model toward adversarial examples is 1%，so the attack success rate (SR) is 99%, I think my code is correct. On 11/23/2018 13:03, Zhaomang Sun wrote: pred_lab = torch.argmax(target_model(adv_img), 1) num_correct += torch.sum(pred_lab==test_label, 0) pred_lab should be equal to targeted label, which is different from ground-truth label — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or mute the thread.

[Sunshine352]

Oh, it's right. But you test SR in the case of targeted attack?

[Sunshine352]

In addition, the line 'num_correct += torch.sum(pred_lab==test_label,0)' , pred_lab is the label of adv-image, test_label is the gt-label. Though target_model acc is high enough, the test-acc in test set is not 100%. So you should conduct the adversarial attack in the correct-classification samples among test set.

[mathcbc]

No, it's untargeted attack. On 11/23/2018 16:55, Zhaomang Sun wrote: Oh, it's right. But you test SR in the case of targeted attack? — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or mute the thread.