针对基于大型语言模型推荐的隐蔽攻击
Stealthy Attack on Large Language Model based Recommendation
AI总结：
本研究揭示了基于LLM的推荐系统因侧重文本内容而存在的新型安全漏洞，提出一种仅需在测试阶段细微修改物品文本即可显著提升其曝光度且不影响整体性能的隐蔽攻击方法。
摘要：
近期，强大的大型语言模型（LLMs）在推动推荐系统（RS）的发展方面发挥了关键作用。然而，尽管这些系统蓬勃发展，其面临安全威胁的脆弱性却在很大程度上被忽视。在本研究中，我们揭示，由于LLMs侧重于物品的文本内容，将其引入推荐模型会带来新的安全漏洞。我们证明，攻击者仅需在测试阶段修改物品的文本内容，即可显著提升该物品的曝光度，而无需直接干预模型的训练过程。此外，该攻击具有极高的隐蔽性，因为它不会影响整体推荐性能，且对文本的修改非常细微，使得用户和平台难以察觉。我们在四个主流的基于LLM的推荐模型上进行的全面实验，证明了我们方法的卓越有效性和隐蔽性。我们的工作揭示了基于LLM的推荐系统中存在的重大安全缺口，并为未来保护这些系统的研究铺平了道路。
英文摘要：
Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely overlooked. In this work, we reveal that the introduction of LLMs into recommendation models presents new security vulnerabilities due to their emphasis on the textual content of items. We demonstrate that attackers can significantly boost an item's exposure by merely altering its textual content during the testing phase, without requiring direct interference with the model's training process. Additionally, the attack is notably stealthy, as it does not affect the overall recommendation performance and the modifications to the text are subtle, making it difficult for users and platforms to detect. Our comprehensive experiments across four mainstream LLM-based recommendation models demonstrate the superior efficacy and stealthiness of our approach. Our work unveils a significant security gap in LLM-based recommendation systems and paves the way for future research on protecting these systems.
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。
