StavC/Here-Comes-the-AI-Worm

Code for paper "MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM safety"

Provides a collection of sandboxes, exploitation code, and tutorials that exemplifies GenAI Red Teaming exercises. It aims to help security researchers and developers test, probe, and evaluate the safety and security of GenAI-based applications.

[NeurIPS 2026] Safety failures in coding agents and frontier LLMs. Reproducible workspaces for studying when AI agents generate unsafe data during task completion.

Proof of concept code for poisoning code generation models.

This repository provides a benchmark for prompt injection attacks and defenses in LLMs

Official implementation of paper: DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers

A repo for all the jailbreaks

New ways of breaking app-integrated LLMs