Pinned

1. smoothing-adversarial Public

   Code for our NeurIPS 2019 *spotlight* "Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers"

   Python 196 36

2. microsoft/robust-models-transfer Public

   Official repository for our NeurIPS 2020 *oral* "Do Adversarially Robust ImageNet Models Transfer Better?"

   Python 194 32

3. microsoft/unadversarial Public

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

   Python 85 16

4. microsoft/denoised-smoothing Public

   Provably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs

   Jupyter Notebook 76 15

5. MadryLab/robustness Public

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

   Jupyter Notebook 682 136

6. libffcv/ffcv Public

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

   Python 2k 101