A Python library for adversarial machine learning focusing on benchmarki...
alpha-beta-CROWN: An Efficient, Scalable and GPU Accelerated Neural Netw...
Square Attack: a query-efficient black-box adversarial attack via random...
[TPAMI2022 & NeurIPS2020] Official implementation of Self-Adaptive Training
Provably defending pretrained classifiers including the Azure, Google, A...
[CVPR 2020] Adversarial Robustness: From Self-Supervised Pre-Training to...
Unofficial implementation of the DeepMind papers "Uncovering the Limits ...
[ICLR 2021] "InfoBERT: Improving Robustness of Language Models from An I...
Feature Scattering Adversarial Training (NeurIPS19)
Pytorch implementation of our NeurIPS'20 *Oral* paper "DVERGE: Diversify...
Lipschitz Neural Networks described in "Sorting Out Lipschitz Function A...
[ICLR 2021] "Robust Overfitting may be mitigated by properly learned smo...
Code for FAB-attack