NEXUS通过构建语义网络提升多轮越狱攻击成功率。
NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks
- 用分层语义网络生成恶意意图的多轮对话路径
- 通过三阶段协作反馈，使攻击成功率提升2.1%~19.4%
- 适合研究模型安全或对抗攻击的人员使用
大型语言模型（LLMs）在自然语言处理中取得突破，但仍易受越狱攻击，尤其是将恶意意图分散在多轮对话中、绕过对齐机制的攻击。现有方法往往对对抗空间探索不足，依赖手工启发式规则，或缺乏系统性查询优化。本文提出NEXUS（Network Exploration for eXploiting Unsafe Sequences），一个用于构建、优化和执行多轮攻击的模块化框架。NEXUS包含：(1) ThoughtNet，将有害意图分层扩展为包含主题、实体和查询链的结构化语义网络；(2) 反馈驱动的Simulator，通过攻击者-受害者-裁判三类LLM协作，基于危害性与语义相似性基准迭代优化并剪枝查询链；(3) Network Traverser，自适应导航优化后的查询空间以实现实时攻击。该流程可发现隐蔽且高成功率的对抗路径。在多个闭源与开源LLM上，相较已有方法，攻击成功率提升2.1%至19.4%。代码已开源。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have revolutionized natural language processing but remain vulnerable to jailbreak attacks, especially multi-turn jailbreaks that distribute malicious intent across benign exchanges and bypass alignment mechanisms. Existing approaches often explore the adversarial space poorly, rely on hand-crafted heuristics, or lack systematic query refinement. We present NEXUS (Network Exploration for eXploiting Unsafe Sequences), a modular framework for constructing, refining, and executing optimized multi-turn attacks. NEXUS comprises: (1) ThoughtNet, which hierarchically expands a harmful intent into a structured semantic network of topics, entities, and query chains; (2) a feedback-driven Simulator that iteratively refines and prunes these chains through attacker-victim-judge LLM collaboration using harmfulness and semantic-similarity benchmarks; and (3) a Network Traverser that adaptively navigates the refined query space for real-time attacks. This pipeline uncovers stealthy, high-success adversarial paths across LLMs. On several closed-source and open-source LLMs, NEXUS increases attack success rate by 2.1% to 19.4% over prior methods. Code: https://github.com/inspire-lab/NEXUS
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。