Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models

Yanjiang Liu, Shuhen Zhou, Yaojie Lu, Huijia Zhu, weyl, Hongyu Lin, Ben He, Xianpei Han, Le Sun

Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models: 17 upvotes on Hugging Face Daily Papers, #10 of 19 papers on 2025-01-07. Day-by-day upvote history.

Automated red-teaming has become a crucial approach for uncovering vulnerabilities in large language models (LLMs). However, most existing methods focus on isolated safety flaws, limiting their ability to adapt to dynamic defenses and uncover complex vulnerabilities efficiently. To address this challenge, we propose Auto-RT, a reinforcement learning framework that automatically explores and optimizes complex attack strategies to effectively uncover security vulnerabilities through malicious queries. Specifically, we introduce two key mechanisms to reduce exploration complexity and improve strategy optimization: 1) Early-terminated Exploration, which accelerate exploration by focusing on high-potential attack strategies; and 2) Progressive Reward Tracking algorithm with intermediate downgrade models, which dynamically refine the search trajectory toward successful vulnerability exploitation. Extensive experiments across diverse LLMs demonstrate that, by significantly improving exploration efficiency and automatically optimizing attack strategies, Auto-RT detects a boarder range of vulnerabilities, achieving a faster detection speed and 16.63\% higher success rates compared to existing methods.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.