Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models. Advbox give a command line tool to generate adversarial examples with Zero-Coding.

SHIELD: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression

A Python library for adversarial machine learning focusing on benchmarking adversarial robustness.

Official implementation of REGroup method proposed in the paper: "Dissecting Deep Networks into an Ensemble of GenerativeClassifiers for Robust Predictions"

Reproduce multiple adversarial attack methods

PyTorch implementation of DeepFool adversarial attack.

Based on Pytorch, the Adversarial Attack algorithm DeepFool, targeting the Mnist data set and ResNet18 network