2025/02/28 by Choi, Chanwoo, Jin-Soo Kim, Soo Ick Cho +4 · 4 citations
Computer Science · Engineering · #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Network Security and Intrusion Detection #Security and Verification in Computing #Smart Grid Security and Resilience
paper · pdf · doi:10.48550/arxiv.2502.20995
openalex publication_date 2025/02/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
With the growing adoption of retrieval-augmented generation (RAG) systems, various attack methods have been proposed to degrade their performance. However, most existing approaches rely on unrealistic assumptions in which external attackers have access to internal components such as the retriever. To address this issue, we introduce a realistic black-box attack based on the RAG paradox, a structural vulnerability arising from the system's effort to enhance trust by revealing both the retrieved documents and their sources to users. This transparency enables attackers to observe which sources are used and how information is phrased, allowing them to craft poisoned documents that are more likely to be retrieved and upload them to the identified sources. Moreover, as RAG systems directly provide retrieved content to users, these documents must not only be retrievable but also appear natural and credible to maintain user confidence in the search results. Unlike prior work that focuses solely on improving document retrievability, our attack method explicitly considers both retrievability and user trust in the retrieved content. Both offline and online experiments demonstrate that our method significantly degrades system performance without internal access, while generating natural-looking poisoned documents.