X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents

Salman Rahman, Liwei Jiang, James Shiffer, Genglin Liu, Sheriff Issaka, Md Rizwan Parvez, Hamid Palangi, Kai-Wei Chang, Yejin Choi, Saadia Gabriel

Keywords: Multi-turn Jailbreaks, Adaptive Multi-Agent, Conversational AI Safety, Red-Teaming, Defensive Alignment

TL;DR: X-Teaming, a scalable multi-agent framework that achieves state-of-the-art multi-turn jailbreaking of language models while X-Guard trains models to defend against these attacks.

Abstract: Multi-turn interactions with language models (LMs) pose critical safety risks, as harmful intent can be strategically spread across exchanges. Yet, the vast majority of prior work has focused on single-turn safety, while adaptability and diversity remain among the key challenges of multi-turn red-teaming. To address these challenges, we present X-Teaming, a scalable framework that systematically explores how seemingly harmless interactions escalate into harmful outcomes and generates corresponding attack scenarios. X-Teaming employs collaborative agents for planning, attack optimization, and verification, achieving state-of-the-art multi-turn jailbreak effectiveness and diversity with success rates up to 98.1% across representative leading open-weight and closed-source models. In particular, X-Teaming achieves a 96.2% attack success rate against the latest Claude 3.7 Sonnet model, which has been considered nearly immune to single-turn attacks. Building on X-Teaming, we introduce X-Guard-Train, an open-source multi-turn safety training dataset that's $~20\times$ larger than the previous best resource, comprising 30K interactive jailbreaks, designed to enable robust multi-turn safety alignment for LMs. Our work offers essential tools and insights for mitigating sophisticated conversational attacks, advancing the multi-turn safety of LMs.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 1770