One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems

[2505.11548] One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Cryptography and Security arXiv:2505.11548 (cs) [Submitted on 15 May 2025 ( v1 ), last revised 9 Apr 2026 (this version, v4)] Title: One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems Authors: Zhiyuan Chang , Mingyang Li , Xiaojun Jia , Junjie Wang , Yuekai Huang , Ziyou Jiang , Yang Liu , Qing Wang View a PDF of the paper titled One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems, by Zhiyuan Chang and 7 other authors View PDF HTML (experimental) Abstract: Large Language Models (LLMs) enhanced with Retrieval-Augmented Generation (RAG) have shown improved performance in generating accurate responses. However, the dependence on external knowledge bases introduces potential security vulnerabilities, particularly when these knowledge bases are publicly accessible and modifiable. While previous studies have exposed knowledge poisoning risks in RAG systems, existing attack methods suffer from critical limitations: they either require injecting multiple poisoned documents (resulting in poor stealthiness) or can only function effectively on simplistic queries (limiting real-world applicability). This paper reveals a more realistic knowledge poisoning attack against RAG systems that achieves successful attacks by poisoning only a single document while remaining effective for complex multi-hop questions involving complex relationships between multiple elements. Our proposed AuthChain address three challenges to ensure the poisoned documents are reliably retrieved and trusted by the LLM, even against large knowledge bases and LLM's own knowledge. Extensive experiments across six popular LLMs demonstrate that AuthChain achieves significantly higher attack success rates while maintaining superior stealthiness against RAG defense mechanisms compared to state-of-the-art baselines. Comments: 15pages, 4 figures; accepted by EMNLP 2025 Findings Subjects: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2505.11548 [cs.CR] (or arXiv:2505.11548v4 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2505.11548 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Zhiyuan Chang [ view email ] [v1] Thu, 15 May 2025 08:14:58 UTC (17,954 KB) [v2] Tue, 20 May 2025 02:50:12 UTC (21,176 KB) [v3] Mon, 1 Sep 2025 02:28:23 UTC (21,700 KB) [v4] Thu, 9 Apr 2026 01:58:59 UTC (21,694 KB) Full-text links: Access Paper: View a PDF of the paper titled One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems, by Zhiyuan Chang and 7 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CR < prev | next > new | recent | 2025-05 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: 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 Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• ToxicRAG: Compromising Retrieval-Augmented Generation Systems via Single-Shot Knowledge Poisoning Attacks#673418
• MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks#798689
• MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks#797275
• TRIS: A Tri-Layer Retrieval Integrity Sieve Against Knowledge Poisoning#819916
• ToxicRAG: Compromising Retrieval-Augmented Generation Systems via Single-Shot Knowledge Poisoning Attacks#998642