A Python library for Secure and Explainable Machine Learning

Contains notebooks for the PAR tutorial at CVPR 2021.

Framework for the Adversarial Machine Learning Challenge at CU Denver, showcasing techniques in AI model defense and attack.

The pretrained TensorFlow Keras models with a Foolbox Zoo compatible interface

A graphical tool to test the robustness of classifiers using Foolbox.

Framework for the Adversarial Machine Learning Challenge at CU Denver, showcasing techniques in AI model defense and attack. Role: Lead developer and competition architect

Defending Against Adversarial Attacks One Layer at a Time