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

Robustness evaluation framework for ML-Based Windows malware detectors

advertorch

A Toolbox for Adversarial Robustness Research

openattack

OpenAttack

neuralsat

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

torchattack

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

torchdefenses

PyTorch implementation of adversarial attacks [torchattacks]

semanticshield

SemanticShield library

aixploit

Engineered to help red teams and penetration testers exploit large language model AI solutions vulnerabilities.

trojanzoo

a universal pytorch platform to conduct security researches

teapot-nlp

Source and target side evaluation of adversarial attacks on NLP models

promptbench

PromptBench is a powerful tool designed to scrutinize and analyze the interaction of large language models with various prompts. It provides a convenient infrastructure to simulate **black-box** adversarial **prompt attacks** on the models and evaluate their performances.

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.

sentinel-llm-security

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

deepapi

Deep Learning Cloud Service for Black-Box Adversarial Attacks

nfl-veripy

Formal verification of neural feedback loops (NFLs)

layerssustainabilityanalysis

LSA : Layer Sustainability Analysis framework for the analysis of layer vulnerability in a given neural network. LSA can be a helpful toolkit to assess deep neural networks and to extend the adversarial training approaches towards improving the sustainability of model layers via layer monitoring and analysis.

torchadv

🔥🛡️⚔️ Tiny package designed to support red teams and penetration testers in creating and analyzing adversarial attacks on PyTorch models.