11 Adversarial Machine Learning Tools and Resources for Robustness Testing, Attacks, and Defense

Open Source Adversarial ML Tools

AdvBox

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.

License: Apache License 2.0

GitHub
Adversarial DNN Playground

think TensorFlow Playground, but for Adversarial Examples! A visualization tool designed for learning and teaching - the attack library is limited in size, but it has a nice front-end to it with buttons you can press!

License: Apache License 2.0

GitHub
AdverTorch

library for adversarial attacks / defenses specifically for PyTorch.

License: GNU Lesser General Public License v3.0

GitHub
CleverHans

library for testing adversarial attacks / defenses maintained by some of the most important names in adversarial ML, namely Ian Goodfellow (ex-Google Brain, now Apple) and Nicolas Papernot (Google Brain). Comes with some nice tutorials!

License: MIT License

GitHub
Counterfit

Counterfit is a command-line tool and generic automation layer for assessing the security of machine learning systems.

License: MIT License

GitHub
DEEPSEC

another systematic tool for attacking and defending deep learning models.

License: MIT License

GitHub
Foolbox

second biggest adversarial library. Has an even longer list of attacks - but no defenses or evaluation metrics. Geared more towards computer vision. Code easier to understand / modify than ART - also better for exploring blackbox attacks on surrogate models.

License: MIT License

GitHub
Website: https://foolbox.jonasrauber.de
Adversarial Robustness Toolbox (ART))

ART provides tools that enable developers and researchers to defend and evaluate Machine Learning models and applications against the adversarial threats of Evasion, Poisoning, Extraction, and Inference.

License: MIT License

GitHub
Website: https://adversarial-robustness-toolbox.readthedocs.io/en/latest/
MIA

A library for running membership inference attacks (MIA) against machine learning models.

License: MIT License

GitHub
TextFool

plausible looking adversarial examples for text generation.

License: MIT License

GitHub
Trickster

Library and experiments for attacking machine learning in discrete domains using graph search.

License: MIT License

GitHub
Website: https://arxiv.org/abs/1810.10939