Adversarial Attacks Python Packages

nlpaug

Data augmentation for NLP

textattack

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

adversarial-robustness-toolbox

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

foolbox

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

torchattacks

PyTorch implementation of adversarial attacks [torchattacks]

aicu-scanner

Black-box security scanner for LLM applications — prompt injection, safety bypass, credential leakage

pyautoattack

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

provael

Provael — red-team open Vision-Language-Action (VLA) robot policies in simulation and report an Attack Success Rate (ASR). Prove it. Prevail.

deeprobust

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

advertorch

A Toolbox for Adversarial Robustness Research

vla-redteam

Provael — red-team open Vision-Language-Action (VLA) robot policies in simulation and report an Attack Success Rate (ASR). Prove it. Prevail.

torchattack

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

adv-lib

Library containing PyTorch implementations of various adversarial attacks and resources

mcp-strike

Active adversarial security scanner for Model Context Protocol (MCP) servers: runtime attacks, LLM-as-judge, and an adaptive agent.

scarecrow-alpr

An adversarial frame pattern optimizer for evading automated license plate recognition, personalized to your plate.

openattack

An Open-Source Package for Textual Adversarial Attack.

neuralsat

A neural network verification tool based on the DPLL(T) SMT Solving algorithm.

vision-des

VisionDES is a vision-oriented Dynamic Ensemble Selection (DES) framework that adapts classical DES techniques to modern deep learning pipelines.

teapot-nlp

Tool for Evaluating Adversarial Perturbations on Text

torchdefenses

PyTorch implementation of adversarial attacks [torchattacks]

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.

aixploit

AI redTeaming Python library

rlm-toolkit

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

semanticshield

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