A minimal yet resourceful implementation of diffusion models (along with pretrained models + synthetic images for nine datasets)

Code for the experiments of the ICML 2021 Interpretability workshop paper "This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks"

RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]

Helper-based Adversarial Training: Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off

Unofficial implementation of the DeepMind papers "Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples" & "Fixing Data Augmentation to Improve Adversarial Robustn…

Deep Learning for Toxic Comment Classification