Adversarial Attacks Python Packages

nlpaug

Data augmentation for NLP

adversarial-robustness-toolbox

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

textattack

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

torchattacks

PyTorch implementation of adversarial attacks [torchattacks]

foolbox

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

pyautoattack

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

deeprobust

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

ml-pentest

This is a software framework that can be used for the evaluation of the robustness of Malware Detection methods with respect to adversarial attacks.

advertorch

A Toolbox for Adversarial Robustness Research

neuralsat

NeuralSAT: A DPLL(T) Framework for Verifying Deep Neural Networks

openattack

An Open-Source Package for Textual Adversarial Attack.

deepdefend

DeepDefend is an open-source Python library for adversarial attacks and defenses in deep learning models, enhancing the security and robustness of AI systems.

torchattack

🛡 A curated list of adversarial attacks in PyTorch, with a focus on transferable black-box attacks.

torchdefenses

Adversarial Defenses for PyTorch

trojanzoo

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

promptbench

A unified evaluation framework for large language models

aixploit

AI redTeaming Python library

dnnf

Deep Neural Network Falsification

deepapi

Deep Learning Cloud Service for Black-Box Adversarial Attacks

semanticshield

The Security Toolkit for managing Generative AI(especially LLMs) and Supervised Learning processes(Learning and Inference).

harmonydagger

A tool for protecting audio against use in AI training

perceptual-advex

Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".

nfl-veripy

Formal Verification of Neural Feedback Loops (NFLs)

sentinel-llm-security

AI Security Platform: Defense (61 Rust engines + Micro-Model Swarm) + Offense (39K+ payloads)