Popular GitHub Repositories for Adversarial Machine Learning

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/

ChatGPT Jailbreaks, GPT Assistants Prompt Leaks, GPTs Prompt Injection, LLM Prompt Security, Super Prompts, Prompt Hack, Prompt Security, Ai Prompt Engineering, Adversarial Machine Learning.

The Security Toolkit for LLM Interactions

A Toolbox for Adversarial Robustness Research

A curated list of useful resources that cover Offensive AI.

A curated list of adversarial attacks and defenses papers on graph-structured data.

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

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.

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

GraphGallery is a gallery for benchmarking Graph Neural Networks, From InplusLab.

Provable adversarial robustness at ImageNet scale

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

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

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

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

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

Create adversarial attacks against machine learning Windows malware detectors