Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

Fawkes, privacy preserving tool against facial recognition systems. More info at https://sandlab.cs.uchicago.edu/fawkes

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

The Security Toolkit for LLM Interactions

RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]

Papers and resources related to the security and privacy of LLMs 🤖

T2F: text to face generation using Deep Learning

Unofficial PyTorch implementation of the paper titled "Progressive growing of GANs for improved Quality, Stability, and Variation"

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

GraphGallery is a gallery for benchmarking Graph Neural Networks

⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs

TransferAttack is a pytorch framework to boost the adversarial transferability for image classification.

Provable adversarial robustness at ImageNet scale

Backdoors Framework for Deep Learning and Federated Learning. A light-weight tool to conduct your research on backdoors.

auto_LiRPA: An Automatic Linear Relaxation based Perturbation Analysis Library for Neural Networks and General Computational Graphs

Create adversarial attacks against machine learning Windows malware detectors

Code for our NeurIPS 2019 *spotlight* "Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers"

A guided mutation-based fuzzer for ML-based Web Application Firewalls

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

MSG-GAN: Multi-Scale Gradients GAN (Architecture inspired from ProGAN but doesn't use layer-wise growing)