提示、分治：通过分段和分布式提示处理绕过大语言模型安全过滤器
Prompt, Divide, and Conquer: Bypassing Large Language Model Safety Filters via Segmented and Distributed Prompt Processing
AI总结：
提出一种结合分布式提示处理和迭代优化的越狱框架，通过提示分段、并行处理、响应聚合及LLM陪审团评估四个模块，在500个恶意提示上实现73.2%的恶意代码生成成功率，并证明分布式架构较非分布式提升12%，同时揭示单LLM评判高估成功率的问题。
摘要：
大语言模型（LLMs）在改变各领域任务自动化和内容生成的同时，也引入了安全过滤器以防止滥用。我们提出了一种新型越狱框架，该框架采用分布式提示处理并结合迭代优化来绕过这些安全措施，特别是在生成恶意代码方面。我们的架构包含四个关键模块：提示分段、并行处理、响应聚合以及基于LLM的陪审团评估。在10个网络安全类别的500个恶意提示上进行测试，该框架在生成恶意代码方面达到了73.2%的成功率（SR）。值得注意的是，我们的比较分析揭示，传统的单LLM评判评估高估了成功率（93.8%），而我们的LLM陪审团系统为73.2%，人工验证证实单评判评估经常接受不完整的实现。此外，我们在消融研究中证明，与未分布式方法相比，我们的分布式架构将成功率提高了12%，这凸显了分布式提示处理的有效性以及稳健评估方法在评估越狱尝试中的重要性。
英文摘要：
Large Language Models (LLMs) have transformed task automation and content generation across various domains while incorporating safety filters to prevent misuse. We introduce a novel jailbreaking framework that employs distributed prompt processing combined with iterative refinements to bypass these safety measures, particularly in generating malicious code. Our architecture consists of four key modules: prompt segmentation, parallel processing, response aggregation, and LLM-based jury evaluation. Tested on 500 malicious prompts across 10 cybersecurity categories, the framework achieves a 73.2% Success Rate (SR) in generating malicious code. Notably, our comparative analysis reveals that traditional single-LLM judge evaluation overestimates SRs (93.8%) compared to our LLM jury system (73.2%), with manual verification confirming that single-judge assessments often accept incomplete implementations. Moreover, we demonstrate that our distributed architecture improves SRs by 12% over the non-distributed approach in an ablation study, highlighting both the effectiveness of distributed prompt processing and the importance of robust evaluation methodologies in assessing jailbreak attempts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
