Adversarial Machine Learning Implementation for existing attacks and defenses:
- ZOO: ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models. Note: this repository contains CW attacks.
- CLEVER: Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
- Feature Squeezing: Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
- MagNet: MagNet: a Two-Pronged Defense against Adversarial Examples
- PGD: Towards Deep Learning Models Resistant to Adversarial Attacks
- Convex adversarial: Provable defenses against adversarial examples via the convex outer adversarial polytope
- AutoZoom AutoZOOM: Autoencoder-based Zeroth Order Optimization Method