CleanBase: Detecting Malicious Documents in RAG Knowledge Databases

• URL: http://arxiv.org/abs/2605.00460v1
• Date: Fri, 01 May 2026 06:51:58 GMT
• Title: CleanBase: Detecting Malicious Documents in RAG Knowledge Databases
• Abstract summary: Retrieval-augmented generation (RAG) is vulnerable to prompt injection attacks.<n>CleanBase is a method to detect malicious documents within a knowledge database.
• Score: 22.879630824002074
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Retrieval-augmented generation (RAG) is vulnerable to prompt injection attacks, in which an adversary inserts malicious documents containing carefully crafted injected prompts into the knowledge database. When a user issues a question targeted by the attack, the RAG system may retrieve these malicious documents, whose injected prompts mislead it into generating attacker-specified answers, thereby compromising the integrity of the RAG system. In this work, we propose CleanBase, a method to detect malicious documents within a knowledge database. Our key insight is that malicious documents crafted for the same attack-targeted questions often exhibit high semantic similarity, as attackers deliberately make them consistent to improve attack success rates. Accordingly, CleanBase constructs a similarity graph over the knowledge database, where each node represents a document and an edge connects two nodes if their semantic similarity--computed using an embedding model--exceeds a statistically determined threshold. Due to their inherent similarity, malicious documents tend to form cliques within this graph. CleanBase detects such cliques and flags the corresponding documents as malicious. We theoretically derive upper bounds on CleanBase's false positive and false negative rates and empirically validate its effectiveness. Experimental results across multiple datasets and prompt injection attacks demonstrate that CleanBase accurately detects malicious documents and effectively safeguards RAG systems. Our source code is available at https://github.com/WeifeiJin/CleanBase.

Related papers

• CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents [29.44505137598001]
  CamoDocs is a poisoning attack that avoids direct query inclusion by camouflaging adversarial documents among benign content.<n>It achieves strong average ASR while avoiding query-overlap artifacts exploited by simple query detection.
  arXiv  Detail & Related papers  (2026-08-28T14:44:28Z)
• From Association to Causation: Improving Retrieval Precision of Retrieval-Augmented Generation via Causal Relations and an Attention Mechanism [23.0538048682894]
  We model the terminal retrieval stage with a causal graph grounded in Reichenbach's common cause principle.<n>Since a retrieved document is a collider (A -> d - B), retrieval itself opens an associational path between the query and B.<n>Unlike causality-enhanced RAG variants that model causal relations inside the knowledge content, our graph models the causal structure of the retrieval process itself.
  arXiv  Detail & Related papers  (2026-08-22T00:31:06Z)
• TopoGuard: Graph Theory Based Defenses Against Split-Knowledge Attacks on RAG [5.328366903719861]
  Production Retrieval Augmented Generation (RAG) systems rely on aggregating external documents to answer complex queries.<n>The retrieved documents introduce a new threat surface that can be exploited to launch split-knowledge attacks.<n>This paper shows that the new attack is structurally invisible to existing per-document filters, like LlamaGuard.<n>To address this issue in RAG, this work introduces TopoGuard, a family of graph theory-based methods specifically targeting the split-knowledge attacks.
  arXiv  Detail & Related papers  (2026-05-11T17:46:02Z)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents [34.909802797979324]
  We present the first comprehensive benchmark study on detecting prompt injection attacks targeting web agents.<n>We construct datasets containing both malicious and benign samples.<n>We then systematize both text-based and image-based detection methods.
  arXiv  Detail & Related papers  (2025-10-01T18:34:06Z)
• VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection [55.957275374847484]
  VulAgent is a multi-agent vulnerability detection framework based on hypothesis validation.<n>It implements a semantics-sensitive, multi-view detection pipeline, each aligned to a specific analysis perspective.<n>On average, VulAgent improves overall accuracy by 6.6%, increases the correct identification rate of vulnerable--fixed code pairs by up to 450%, and reduces the false positive rate by about 36%.
  arXiv  Detail & Related papers  (2025-09-15T02:25:38Z)
• Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning [58.57194301645823]
  Large language models (LLMs) are increasingly integrated into real-world personalized applications.<n>The valuable and often proprietary nature of the knowledge bases used in RAG introduces the risk of unauthorized usage by adversaries.<n>Existing methods that can be generalized as watermarking techniques to protect these knowledge bases typically involve poisoning or backdoor attacks.<n>We propose name for harmless' copyright protection of knowledge bases.
  arXiv  Detail & Related papers  (2025-02-10T09:15:56Z)
• On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains [32.71308102835446]
  Retrieval-Augmented Generation (RAG) has been empirically shown to enhance the performance of large language models (LLMs) in knowledge-intensive domains.<n>We show that RAG is vulnerable to universal poisoning attacks in medical Q&A.<n>We develop a new detection-based defense to ensure the safe use of RAG.
  arXiv  Detail & Related papers  (2024-09-12T02:43:40Z)
• BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models [18.107026036897132]
  Large Language Models (LLMs) are constrained by outdated information and a tendency to generate incorrect data. Retrieval-Augmented Generation (RAG) addresses these limitations by combining the strengths of retrieval-based methods and generative models. RAG introduces a new attack surface for LLMs, particularly because RAG databases are often sourced from public data, such as the web.
  arXiv  Detail & Related papers  (2024-06-03T02:25:33Z)
• Verifying the Robustness of Automatic Credibility Assessment [50.55687778699995]
  We show that meaning-preserving changes in input text can mislead the models. We also introduce BODEGA: a benchmark for testing both victim models and attack methods on misinformation detection tasks. Our experimental results show that modern large language models are often more vulnerable to attacks than previous, smaller solutions.
  arXiv  Detail & Related papers  (2023-03-14T16:11:47Z)
• Precise Zero-Shot Dense Retrieval without Relevance Labels [60.457378374671656]
  Hypothetical Document Embeddings(HyDE) is a zero-shot dense retrieval system. We show that HyDE significantly outperforms the state-of-the-art unsupervised dense retriever Contriever.
  arXiv  Detail & Related papers  (2022-12-20T18:09:52Z)
• Open-sourced Dataset Protection via Backdoor Watermarking [87.15630326131901]
  We propose a emphbackdoor embedding based dataset watermarking method to protect an open-sourced image-classification dataset. We use a hypothesis test guided method for dataset verification based on the posterior probability generated by the suspicious third-party model.
  arXiv  Detail & Related papers  (2020-10-12T16:16:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.