-
Notifications
You must be signed in to change notification settings - Fork 110
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Adversarials are equals to originals #64
Comments
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 |
Yes, I cloned the last version of the code and set
But I still become tensors which are equals to input. Did you use last version of code in your test? |
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? |
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 |
Hi. I run
autoattack
using your exampleautoattack/examples/eval.py
:But the result adversarials are equals to original inputs:
I tried to use
epsilon = 8./255.
andepsilon = 0.5
. The result was not changed((Could you please explain me where i am wrong?
The text was updated successfully, but these errors were encountered: