14 open source projects by MadryLab

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

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

Code for "Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors"

Fine-grained ImageNet annotations

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

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

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

Code for "Robustness May Be at Odds with Accuracy"

A lightweight experimental logging library

Certified Patch Robustness via Smoothed Vision Transformers

Investigating the robustness of state-of-the-art CNN architectures to simple spatial transformations.

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

No description, website, or topics provided.