arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.03589cs.CL
收藏

对话式搜索引擎的排名操纵

Ranking Manipulation for Conversational Search Engines

UC Berkeley(加州大学伯克利分校)

Samuel Pfrommer, Yatong Bai, Tanmay Gautam, Somayeh Sojoudi

AI总结:

本研究调查了提示注入对对话式搜索引擎来源排名的影响,提出基于攻击树的越狱技术,能有效提升低排名产品并迁移至 perplexity.ai 等先进系统,揭示了排名操纵的财务动机与鲁棒性研究的紧迫性。

摘要:

主要搜索引擎提供商正迅速整合大型语言模型(LLM)生成的内容来响应用户查询。这些对话式搜索引擎通过将检索到的网站文本加载到 LLM 上下文中进行总结和解释来运作。最近的研究表明,LLM 极易受到越狱和提示注入攻击,这些攻击利用对抗性字符串破坏 LLM 的安全性和质量目标。本研究调查了提示注入对对话式搜索引擎引用来源排名顺序的影响。为此,我们引入了一个包含真实消费产品网站的专用数据集,并将对话式搜索排名形式化为一个对抗性问题。在实验中,我们分析了无对抗性注入时的对话式搜索排名,结果表明不同 LLM 在优先考虑产品名称、文档内容和上下文位置方面存在显著差异。随后,我们提出了一种基于攻击树的越狱技术,该技术能可靠地提升低排名产品。重要的是,这些攻击能有效迁移到 perplexity.ai 等最先进的对话式搜索引擎。鉴于网站所有者有强烈的财务动机来提升其搜索排名,我们认为我们的问题表述对未来的鲁棒性研究至关重要。

英文摘要:

Major search engine providers are rapidly incorporating Large Language Model (LLM)-generated content in response to user queries. These conversational search engines operate by loading retrieved website text into the LLM context for summarization and interpretation. Recent research demonstrates that LLMs are highly vulnerable to jailbreaking and prompt injection attacks, which disrupt the safety and quality goals of LLMs using adversarial strings. This work investigates the impact of prompt injections on the ranking order of sources referenced by conversational search engines. To this end, we introduce a focused dataset of real-world consumer product websites and formalize conversational search ranking as an adversarial problem. Experimentally, we analyze conversational search rankings in the absence of adversarial injections and show that different LLMs vary significantly in prioritizing product name, document content, and context position. We then present a tree-of-attacks-based jailbreaking technique which reliably promotes low-ranked products. Importantly, these attacks transfer effectively to state-of-the-art conversational search engines such as perplexity$.$ai. Given the strong financial incentive for website owners to boost their search ranking, we argue that our problem formulation is of critical importance for future robustness work.

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。

↑