
PyRIT
Open-source framework for red-teaming generative AI systems: automate attack prompts, score model responses, and audit behavior to identify security…

Open-source framework for red-teaming generative AI systems: automate attack prompts, score model responses, and audit behavior to identify security…

A collection of awesome resources related AI security

Adversary Emulation Framework

Open-source adversary emulation for AI agents and MCP servers.

The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to…

MAAD Attack Framework - An attack tool for simple, fast & effective security testing of M365 & Entra ID (Azure AD).

Generate Linux executables that simulate adversary behaviors and techniques for testing detection and response coverage. Consumes JSON for easy…

An Open-Source Package for Textual Adversarial Attack.