Adversarials are equals to originals about auto-attack HOT 4 OPEN

Hi,

I tried to run the example with the same parameters as yours, and I get the perturbed images as output. Is the log fine (all attacks should give robust accuracy of 0% for epsilon = 8/255)?

from auto-attack.

Yes, I cloned the last version of the code and set epsilon = 8./255.. Here are my logs:

Files already downloaded and verified
setting parameters for standard version
using standard version including apgd-ce, apgd-t, fab-t, square
robust accuracy by APGD-CE 	 0.00% 	 (time attack: 0.0 s)
robust accuracy by APGD-T 	 0.00% 	 (time attack: 0.0 s)
robust accuracy by FAB-T 	 0.00% 	 (time attack: 0.0 s)
robust accuracy by SQUARE 	 0.00% 	 (time attack: 0.0 s)

But I still become tensors which are equals to input. Did you use last version of code in your test?

from auto-attack.

Yeah. I think there's some problem in the loading of your model, since the runtime is 0.0s which suggests that all images are already misclassified. Could you please check the clean accuracy of the classifier?

from auto-attack.

Oh, sorry. I found my error. I used the model pretrained on ImageNet, but call AutoAttac with y_test from CIFAR-10. When I have fix it, everything started work fine

from auto-attack.