Pretrained TorchVision models on CIFAR10 dataset (with weights)

Download files from Google Drive using Python 2 or Python 3

Datasets for the paper "Adversarial Examples are not Bugs, They Are Features"

Code for "Robustness May Be at Odds with Accuracy"

A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.

Notebooks for reproducing the paper "Computer Vision with a Single (Robust) Classifier"

Code for "Learning Perceptually-Aligned Representations via Adversarial Robustness"

Codebase for "Exploring the Landscape of Spatial Robustness" (ICML'19, https://arxiv.org/abs/1712.02779).

HotCRP conference review software

A challenge to explore adversarial robustness of neural networks on CIFAR10.

A challenge to explore adversarial robustness of neural networks on MNIST.