当搜索出错时:针对具有网络搜索功能的大型语言模型的红队测试
When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models
AI总结:
本文提出CREST-Search框架,针对具有网络搜索功能的LLM的安全性问题,通过三种新型攻击策略和迭代上下文优化机制,揭示网络搜索带来的安全漏洞。
摘要:
大型语言模型(LLMs)通过接入实时互联网信息来克服静态知识边界限制。尽管这种整合增强了模型能力,但也引入了新的安全威胁:检索和引用过程可能暴露用户于有害或低可信度的网络内容。现有红队测试方法主要针对独立LLM,忽视了复杂搜索流程中出现的风险。为此,我们提出了CREST-Search,一种针对具有网络搜索功能的LLM的开创性红队测试框架。其核心是三种新的攻击策略,能够生成看似无害的搜索查询但诱导不安全引用。同时,它采用迭代上下文优化机制,在黑盒约束下增强对抗效果。此外,我们构建了一个专门针对搜索的有害数据集WebSearch-Harm,使红队模型能够改进查询质量。实验表明,CREST-Search能够有效绕过安全过滤器,并系统性地揭示基于网络搜索的LLM系统的漏洞,凸显了开发稳健搜索模型的必要性。
英文摘要:
Large Language Models (LLMs) have been augmented with web search to overcome the limitations of the static knowledge boundary by accessing up-to-date information from the open Internet. While this integration enhances model capability, it also introduces a distinct safety threat surface: the retrieval and citation process has the potential risk of exposing users to harmful or low-credibility web content. Existing red-teaming methods are largely designed for standalone LLMs as they primarily focus on unsafe generation, ignoring risks emerging from the complex search workflow. To address this gap, we propose CREST-Search, a pioneering red-teaming framework for LLMs with web search. The cornerstone of CREST-Search is three novel attack strategies that generate seemingly benign search queries yet induce unsafe citations. It also employs an iterative in-context refinement mechanism to strengthen adversarial effectiveness under black-box constraints. In addition, we construct a search-specific harmful dataset, WebSearch-Harm, which enables fine-tuning a specialized red-teaming model to improve query quality. Our experiments demonstrate that CREST-Search can effectively bypass safety filters and systematically expose vulnerabilities in web search-based LLM systems, underscoring the necessity of the development of robust search models.
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。