LTS4 / DeepFool

A simple and accurate method to fool deep neural networks
356 stars 130 forks source link

small implementation error in torchattacks.DeepFool #10

Open LaurenzBeck opened 2 years ago

LaurenzBeck commented 2 years ago

I currently use DeepFool as an estimate for the distance to the decision boundary of a classifier, as suggested in the paper: https://arxiv.org/abs/2002.01810v1

I used the implementation from torchattacks because I found the implementation from the LTS4/DeepFool repo hard to understand and work without throwing errors. In the implementation from torchattacks I found an implementation error, that returned the original images as perturbation when the classifier already misclassified the image. https://github.com/Harry24k/adversarial-attacks-pytorch/issues/51

This might also be the case in this repo, but I havent checked, just wanted to let you know.