MAIR
MAIR copied to clipboard
PyTorch implementation of adversarial training and defenses [Fantastic Robustness Measures: The Secrets of Robust Generalization, NeurIPS 2023].
I want to evaluate the transferability of attacks between models. E.g., the image attacked using PGM for one model, fed to another model. Do you know of any library that...
Thank you for your contributions, but I'd like to know how to set the beta for TRADES and MART.
Thanks for this amazing repository.