AI45Lab/MAGIC

Official implementation of AdvGame https//arxiv.org/abs/2512.20806

Toolbox to run adversarial attacks against LLM.

[NeurIPS 2025] BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models

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

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

An easy-to-use Python framework to generate adversarial jailbreak prompts.

[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"

[ICML 2025] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".

LLM Adversarial Robustness Toolkit, a toolkit for evaluating LLM robustness through adversarial testing.