Tools

owasp/damn-vulnerable-ml-model

Intentionally vulnerable machine learning model for hands-on security training. Explore common ML vulnerabilities, adversarial attacks, and defensive…

seldonio/alibi-detect

Algorithms for outlier, adversarial and drift detection

trusted-ai/adversarial-robustness-toolbox

Python library for adversarial machine learning security, enabling red and blue teams to run evasion, poisoning, extraction, and inference attacks…

cleverhans-lab/cleverhans

An adversarial example library for constructing attacks, building defenses, and benchmarking both

bethgelab/foolbox

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

madrylab/robustness

Train, evaluate, and explore neural networks with built-in adversarial robustness tools, including PGD attacks, adversarial training, and robust…

thunlp/openattack

An Open-Source Package for Textual Adversarial Attack.

robustbench/robustbench

Standardized adversarial robustness benchmark with a public leaderboard and downloadable model zoo for evaluating ML models against Lp attacks and…

cyberforce/pesidious

Malware Mutation Using Reinforcement Learning and Generative Adversarial Networks

ghostwolflab/ai_security_top

A structured knowledge base covering AI security fundamentals, threat modeling, red team offensive techniques, and blue team defenses, including LLM…

matheusht/redthread

An autonomous red-teaming engine for LLMs. RedThread manages the full security lifecycle: generating adversarial attacks, executing precision…

nccgroup/ml-for-rngs

Demonstrates using machine learning to predict random number generator sequences, highlighting cryptographic weaknesses through adversarial analysis.

telefonica/omlasp

Framework for auditing machine learning algorithms against adversarial attacks and biases, providing educational tools and an academic paper to…

pwnhyo/t-map

Trajectory-aware evolutionary search framework for red-teaming LLM agents over MCP servers, generating adversarial prompts to map vulnerability…

xuyw-seu/packetpatch

Practical black-box adversarial packet generation against encrypted traffic classification with minimal overhead and full packet recoverability.

jinxhy/awesome-moai-security

Curated reading list and taxonomy of attack and defense research for mobile on-device AI systems, covering adversarial, backdoor, model stealing, and…

sec5gloc/sec5gloc

Adversary-resilient deep learning architecture for secure 5G indoor localization, combining CNN and multi-head attention to defend against signal…

sbamit/exponentiated-gradient-descent-llm-attack

A novel adversarial attack on LLM based on the Exponentiated Gradient Descent technique.