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

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

image scaling attacks for multi-modal prompt injection

Python PoC for CVE-2026-21010 that replays captured SIP digest Authorization headers to bypass nonce uniqueness/expiration and make unauthorized VoIP…

Fully automatic censorship removal for language models

An information security preparedness tool to do adversarial simulation.

Adversarial image perturbation tool that uses SAM segmentation and CLIP models to evade AI-based scam image classifiers for security research.

Experiments for control-token chain-of-thought suppression and parser-leniency attacks on tool-using LLM agents

A windows token impersonation tool

Proof-of-concept exploit for CVE-2026-21003 demonstrating JWT authentication bypass by omitting the kid header and using the 'none' algorithm to…

Malware Mutation Using Reinforcement Learning and Generative Adversarial Networks