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

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

A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

A unified evaluation framework for large language models

PyTorch implementation of adversarial attacks [torchattacks]

Must-read Papers on Textual Adversarial Attack and Defense

A pytorch adversarial library for attack and defense methods on images and graphs

A collection of anomaly detection methods (iid/point-based, graph and time series) including active learning for anomaly detection/discovery, bayesian rule-mining, description for diversity/explanation/interpretability. Analysis of incorporating label feedback with ensemble and tree-based detectors. Includes adversarial attacks with Graph Convol…

An Open-Source Package for Textual Adversarial Attack.

This repository is a compilation of all APT simulations that target many vital sectors,both private and governmental. The simulation includes written tools, C2 servers, backdoors, exploitation techniques, stagers, bootloaders, and many other tools that attackers might have used in actual attacks. These tools and TTPs are simulated here.

Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"

A Harder ImageNet Test Set (CVPR 2021)

A Model for Natural Language Attack on Text Classification and Inference

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

PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022

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

Implementation of Papers on Adversarial Examples

🔥🔥Defending Against Deepfakes Using Adversarial Attacks on Conditional Image Translation Networks

TrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classification in deep learning.

Implementation of the KDD 2020 paper "Graph Structure Learning for Robust Graph Neural Networks"