Influence Factors on RAG Poisoning

Computer Science > Cryptography and Security [Submitted on 9 Jun 2026] Influence Factors on RAG Poisoning Pedro Pereira, Eva Maia, Isabel Praça, Adrien Bécue Retrieval-Augmented Generation (RAG) systems enhance large language models by grounding responses in retrieved documents from external knowledge sources at inference time. However, this reliance on retrieved content introduces vulnerabilities to poisoning attacks, in which adversarial documents can manipulate both the retrieval process and the generated outputs. This paper investigates poisoning robustness in RAG through a full factorial experimental study covering 432 configurations. We analyze the impacts of dataset, retriever type, retrieval depth, database composition, chunking strategy, and generator model on retrieval-level and generation-level metrics. The results show that retriever architecture, dataset, and retrieval depth are the strongest factors affecting poisoning exposure, while generator choice and database composition have a major impact on downstream attack success. Dense and graph-based retrievers generally improve robustness relative to BM25, whereas larger retrieval depth increases the likelihood of retrieving poisoned passages. We further show that replicating poisoned content across multiple databases amplifies adversarial influence, while additional clean sources can mitigate it. These findings highlight that poisoning vulnerability in RAG is not attributable to a single component, but instead arises from the interaction of retrieval, generation, and knowledge-base configuration. Comments: 10 pages, 3 figures, 2 Tables, conference KES-2026 30th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2606.12469 [cs.CR]   (or arXiv:2606.12469v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.12469 Focus to learn more Submission history From: Pedro Pereira [view email] [v1] Tue, 9 Jun 2026 19:07:42 UTC (4,607 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 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?)