Saved in:
Bibliographic Details
Main Authors: Yan, Siyu, Zeng, Long, Wu, Xuecheng, Han, Chengcheng, Zhang, Kongcheng, Peng, Chong, Cao, Xuezhi, Cai, Xunliang, Guo, Chenjuan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.14651
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • As large language models~(LLMs) become widely adopted, ensuring their alignment with human values is crucial to prevent jailbreaks where adversaries manipulate models to produce harmful content. While most defenses target single-turn attacks, real-world usage often involves multi-turn dialogues, exposing models to attacks that exploit conversational context to bypass safety measures. We introduce MUSE, a comprehensive framework tackling multi-turn jailbreaks from both attack and defense angles. For attacks, we propose MUSE-A, a method that uses frame semantics and heuristic tree search to explore diverse semantic trajectories. For defense, we present MUSE-D, a fine-grained safety alignment approach that intervenes early in dialogues to reduce vulnerabilities. Extensive experiments on various models show that MUSE effectively identifies and mitigates multi-turn vulnerabilities. Code is available at \href{https://github.com/yansiyu02/MUSE}{https://github.com/yansiyu02/MUSE}.