Updated 10 months ago
attention-meets-perturbation
📝 Official Implementation of "Attention Meets Perturbation: Robust and Interpretable Attention with Adversarial Training"
Updated 10 months ago
adversarial-patch-training
Code for the paper: Adversarial Training Against Location-Optimized Adversarial Patches. ECCV-W 2020.
Updated 10 months ago
https://github.com/cgcl-codes/transferattacksurrogates
The official code of IEEE S&P 2024 paper "Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability". We study how to train surrogates model for boosting transfer attack.