32 Open Source Adversarial Example Software Projects

A non-targeted adversarial attack method, which won the first place in NIPS 2017 non-targeted adversarial attacks competition

A targeted adversarial attack method, which won the NIPS 2017 targeted adversarial attacks competition

Tensorflow Implementation of adversarial learning based adversarial example generator

Tensorflow Implementation of Adversarial Attack to Capsule Networks

My entry for ICLR 2018 Reproducibility Challenge for paper Synthesizing robust adversarial examples https://openreview.net/pdf?id=BJDH5M-AW

reproduction of Thermometer Encoding: One Hot Way To Resist Adversarial Examples in pytorch

基于深度学习的验证码破解、对抗与反对抗研究

Pytorch implementation of convolutional neural network adversarial attack techniques

PyTorch library for adversarial attack and training

Deflecting Adversarial Attacks with Pixel Deflection

Capsule networks can defend against adversarial attacks using reconstruction error

Simple pytorch implementation of FGSM and I-FGSM

Wasserstein Introspective Neural Networks (CVPR 2018 Oral)

Generative Adversarial Perturbations (CVPR 2018)

Spatially Transformed Adversarial Examples with TensorFlow

code for ACL 2018 paper by Kang et al., "AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples "

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.

Code for the CVPR 2019 article "Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses"

A Toolbox for Adversarial Robustness Research

This is a toolbox to construct adversarial examples of EEG signals. The traditional EEG extraction methods and classifiers are re-implemented in Tensorflow.

Adversarial Examples on KNN (and its neural network friends)

Data augmentation for NLP

Official TensorFlow Implementation of Adversarial Training for Free! which trains robust models at no extra cost compared to natural training.

[ICML 2019] ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation

Experiments with distributionally robust optimization (DRO) for deep neural networks

Project page for our paper: Interpreting Adversarially Trained Convolutional Neural Networks

A Harder ImageNet Test Set (CVPR 2021)

An Open-Source Package for Textual Adversarial Attack.

This is the course project for CSCE585: ML Systems. Students will build their machine learning systems based on the provided infrastructure --- Athena.

List of state of the art papers, code, and other resources

TensorFlow version of SqueezeNet with converted pretrained weights

A simple implement of an Adversarial Autoencoding ATN(AAE ATN)