When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse

Computer Science > Cryptography and Security [Submitted on 7 Aug 2026] When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse Yingtao Ren, Ziyi Zhao, Yiwei Fu, Xiao Luo, Yu-Cheng Chang, Chin-Teng Lin Retrieval-augmented generation (RAG) is indispensable for enhancing large language models. However, RAGs are increasingly susceptible to poisoning attacks, in which adversarial documents are injected to manipulate generator outputs. Previous methods rely on output-side signals such as perplexity and consistency checks to detect such attacks. Nevertheless, our analysis reveals that deliberate attacks often induce false confidence, where poisoned outputs exhibit even lower perplexity than benign ones, rendering uncertainty-based detection ineffective. To address this challenge, we explore the internal dynamics of the generator and identify a distinctive signature termed \textit{Attention Collapse}. Unlike the dispersed attention in benign generations, attacked generations exhibit a decrease in entropy as attention concentrates on poisoned documents. Building on these findings, we propose \texttt{D-SCAN} (Document-level Signal Collapse Analysis), a lightweight detection framework that monitors attention dynamics to identify attacked generations. Extensive experiments on multiple attack benchmarks demonstrate the effectiveness of our method. Moreover, D-SCAN can detect attacks even when they fail to alter the final answer. Code is available at this https URL. Comments: Accepted by SIGIR2026 Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2608.06947 [cs.CR]   (or arXiv:2608.06947v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2608.06947 Focus to learn more Related DOI: https://doi.org/10.1145/3805712.3809904 Focus to learn more Submission history From: Yingtao Ren [view email] [v1] Fri, 7 Aug 2026 08:23:26 UTC (339 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-08 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)