Harry24k / adversarial-attacks-pytorch

PyTorch implementation of adversarial attacks [torchattacks]

Home Page:https://adversarial-attacks-pytorch.readthedocs.io/en/latest/index.html

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Implementation of SuperDeepFool attack

alirezaabdollahpour opened this issue · comments

✨ Short description of the feature [tl;dr]

SuperDeepFool is a state-of-the-art minimum-norm adversarial attack proposed in this paper. The original implementation of the SuperDeepFool attack is located here based on the structure of the "torchattacks library."
Please add this attack to the torch attack list.

💬 Detailed motivation and codes

The implementation of SuperDeepFool is straightforward. It is heavily based on the structure of the "torch attacks library."

It seems that you are the author of this attack method, so maybe it would be better if you came to modify and submit to torchattacks. 😀