How to evaluate adversarial machine learning tools

Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow

CTF challenge demonstrating adversarial-image attacks against neural-network image classifiers

Library of defense methods for ML models against adversarial attacks

Python toolbox for adversarial robustness research

Multimodal data-augmentation library for evaluating and improving model robustness; it is not an adversarial-attack generator

A library of adversarial examples and defenses for machine learning models

Proof of concept for training a surrogate convolutional neural network from black-box queries

Deep-pwning is a lightweight framework for experimenting with machine learning models with the goal of evaluating their robustness against a motivated adversary

Python toolbox for creating and evaluating adversarial attacks and defenses

Proof of concept for training a functional surrogate from black-box model queries

Knowledge base of adversary tactics and techniques against AI systems; successor to the deprecated Adversarial ML Threat Matrix

Cloud framework for interactive experimentation with adversarial machine learning research

A framework for implementing Model Inversion attacks

Offensive ML Playbook. Notes on machine learning attacks and pentesting

An Open-Source Package for Textual Adversarial Attack

Source code of the paper "Raze to the Ground: Query-Efficient Adversarial HTML Attacks on Machine-Learning Phishing Webpage Detectors" accepted at AISec '23

TextAttack is a Python framework for adversarial attacks, data augmentation, and model training in NLP

A Model for Natural Language Attack on Text Classification and Inference

Jupyter Attack framework