Adversarial Machine Learning Python Packages

llm-guard

The Security Toolkit for LLM Interactions

adversarial-robustness-toolbox

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

augmented-pca

Repository for the AugmentedPCA Python package.

nuguard

AI red-teaming tool and LLM security framework to evaluate agentic AI applications. Tests prompt injections, handles vulnerability assessment, SBOM generation, and static analysis.

ethicore-engine-selfhost

Ethicore Engine® is an AI safety, ethics, and compliance platform. This repo consists of the open-source components of Ethicore Engine™ - Guardian SDK; designed to protect your AI applications from prompt injection, jailbreaks, role hijacking, system-prompt extraction, and 100+ additional threat categories through a multi-layer analysis pipeline

textattack

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

advertorch

A Toolbox for Adversarial Robustness Research

ethicore-engine-guardian

Ethicore Engine® is an AI safety, ethics, and compliance platform. This repo consists of the open-source components of Ethicore Engine™ - Guardian SDK; designed to protect your AI applications from prompt injection, jailbreaks, role hijacking, system-prompt extraction, and 100+ additional threat categories through a multi-layer analysis pipeline

robustbench

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

adversarial-labeller

Adversarial labeller is a sklearn compatible instance labelling tool for model selection under data drift.

secml

A Python library for Secure and Explainable Machine Learning

whitebox-adversarial-toolbox

Real-time White-Box attacks against Object Detection.

fawkes

Fawkes, privacy preserving tool against facial recognition systems. More info at https://sandlab.cs.uchicago.edu/fawkes

graphgallery

GraphGallery is a gallery for benchmarking Graph Neural Networks

secml-malware

Create adversarial attacks against machine learning Windows malware detectors

asr-attacks

An ASR (Automatic Speech Recognition) adversarial attack repository.

trojai

A repository to quickly generate synthetic data and associated trojaned deep learning models

aixploit

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

memora-swarm

Bit-exact Byzantine-fault-tolerant state layer for federated learning and edge/defence swarms — client SDK, framework adapters, docs & validation battery for the Memora consensus engine.

scratchai-nightly

scratchai is a Deep Learning library that aims to store all Deep Learning algorithms. With easy calls to do all the common tasks in AI.

auto-lirpa

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

lurescope

Deployable fraud-lure scoring API with a live adversarial-evasion demo — companion to LureBench

memora-autogen

Bit-exact Byzantine-fault-tolerant state layer for federated learning and edge/defence swarms — client SDK, framework adapters, docs & validation battery for the Memora consensus engine.

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.