zoeleeee

adversarial-training

blackbox-attack

Blackbox attacks for deep neural network models

cleverhans

An adversarial example library for constructing attacks, building defenses, and benchmarking both

ensemble-detection-attacks

The code from our paper, Adversarial Example Defense: Ensembles of Weak Defenses are not Strong

fast-autoaugment

Official Implementation of 'Fast AutoAugment' in PyTorch.

GAT-ImageNet

GAT: Generative Adversarial Training for Adversarial Example Detection and Robust Classification

GAT-MNIST

GAT: Generative Adversarial Training for Adversarial Example Detection and Robust Classification

HSJA

MagNet

MagNet: a Two-Pronged Defense against Adversarial Examples

ML-LOO

mnist_challenge

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

nn_robust_attacks

Robust evasion attacks against neural network to find adversarial examples

noise

rnd_train

robustness

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

SpectralNormalizationKeras

Spectral Normalization for Keras Dense and Convolution Layers