FFCV: Fast Forward Computer Vision (and other ML workloads!)

Supercharge Your Model Training

A framework for analyzing computer vision models with simulated data

Official repository for our NeurIPS 2021 paper "Unadversarial Examples: Designing Objects for Robust Vision"

Repository for reproducing `Model-Based Robust Deep Learning`

Code for the paper: Adversarial Training Against Location-Optimized Adversarial Patches. ECCV-W 2020.

Code for the paper "(De)Randomized Smoothing for Certifiable Defense against Patch Attacks" by Alexander Levine and Soheil Feizi.

Evaluating Robustness of Neural Networks with Mixed Integer Programming