Disabling Self-Correction in Retrieval-Augmented Generation via Stealthy Retriever Poisoning

• URL: http://arxiv.org/abs/2508.20083v1
• Date: Wed, 27 Aug 2025 17:49:28 GMT
• Title: Disabling Self-Correction in Retrieval-Augmented Generation via Stealthy Retriever Poisoning
• Authors: Yanbo Dai, Zhenlan Ji, Zongjie Li, Kuan Li, Shuai Wang,
• Abstract summary: Retrieval-Augmented Generation (RAG) has become a standard approach for improving the reliability of large language models (LLMs)<n>This paper uncovers that such attacks could be mitigated by the strong textitself-correction ability (SCA) of modern LLMs.<n>We introduce textscDisarmRAG, a new poisoning paradigm that compromises the retriever itself to suppress the SCA and enforce attacker-chosen outputs.
• Score: 14.419943772894754
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Retrieval-Augmented Generation (RAG) has become a standard approach for improving the reliability of large language models (LLMs). Prior work demonstrates the vulnerability of RAG systems by misleading them into generating attacker-chosen outputs through poisoning the knowledge base. However, this paper uncovers that such attacks could be mitigated by the strong \textit{self-correction ability (SCA)} of modern LLMs, which can reject false context once properly configured. This SCA poses a significant challenge for attackers aiming to manipulate RAG systems. In contrast to previous poisoning methods, which primarily target the knowledge base, we introduce \textsc{DisarmRAG}, a new poisoning paradigm that compromises the retriever itself to suppress the SCA and enforce attacker-chosen outputs. This compromisation enables the attacker to straightforwardly embed anti-SCA instructions into the context provided to the generator, thereby bypassing the SCA. To this end, we present a contrastive-learning-based model editing technique that performs localized and stealthy edits, ensuring the retriever returns a malicious instruction only for specific victim queries while preserving benign retrieval behavior. To further strengthen the attack, we design an iterative co-optimization framework that automatically discovers robust instructions capable of bypassing prompt-based defenses. We extensively evaluate DisarmRAG across six LLMs and three QA benchmarks. Our results show near-perfect retrieval of malicious instructions, which successfully suppress SCA and achieve attack success rates exceeding 90\% under diverse defensive prompts. Also, the edited retriever remains stealthy under several detection methods, highlighting the urgent need for retriever-centric defenses.

Related papers

• RAGPart & RAGMask: Retrieval-Stage Defenses Against Corpus Poisoning in Retrieval-Augmented Generation [43.85099769473328]
  Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm to enhance large language models.<n>Recent studies have exposed a critical vulnerability in RAG pipelines corpus poisoning where adversaries inject malicious documents into the retrieval corpus to manipulate model outputs.<n>We propose two complementary retrieval-stage defenses: RAGPart and RAGMask.
  arXiv  Detail & Related papers  (2025-12-30T14:43:57Z)
• 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)
• Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systems [11.812488957698038]
  Large language models (LLMs) are reshaping numerous facets of our daily lives, leading widespread adoption as web-based services.<n>Retrieval-Augmented Generation (RAG) has emerged as a promising direction by generating responses grounded in external knowledge sources.<n>Recent studies demonstrate the vulnerability of RAG, such as knowledge corruption attacks by injecting misleading information.<n>In this work, we introduce RAGDefender, a resource-efficient defense mechanism against knowledge corruption.
  arXiv  Detail & Related papers  (2025-11-03T06:39:58Z)
• RIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning [23.957879891712306]
  We propose an end-to-end attack pipeline that treats the target RAG system as a black box.<n>We demonstrate that this method can effectively execute poisoning attacks against most complex RAG systems.
  arXiv  Detail & Related papers  (2025-10-11T04:23:20Z)
• Benchmarking Misuse Mitigation Against Covert Adversaries [80.74502950627736]
  Existing language model safety evaluations focus on overt attacks and low-stakes tasks.<n>We develop Benchmarks for Stateful Defenses (BSD), a data generation pipeline that automates evaluations of covert attacks and corresponding defenses.<n>Our evaluations indicate that decomposition attacks are effective misuse enablers, and highlight stateful defenses as a countermeasure.
  arXiv  Detail & Related papers  (2025-06-06T17:33:33Z)
• Robust Anti-Backdoor Instruction Tuning in LVLMs [53.766434746801366]
  We introduce a lightweight, certified-agnostic defense framework for large visual language models (LVLMs)<n>Our framework finetunes only adapter modules and text embedding layers under instruction tuning.<n>Experiments against seven attacks on Flickr30k and MSCOCO demonstrate that ours reduces their attack success rate to nearly zero.
  arXiv  Detail & Related papers  (2025-06-04T01:23:35Z)
• The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems [101.68501850486179]
  We explore adversarial attacks against retrieval-augmented generation (RAG) systems to identify their vulnerabilities.<n>This task aims to find imperceptible perturbations that retrieve a target document, originally excluded from the initial top-$k$ candidate set.<n>We propose ReGENT, a reinforcement learning-based framework that tracks interactions between the attacker and the target RAG.
  arXiv  Detail & Related papers  (2025-05-24T08:19:25Z)
• Wolf Hidden in Sheep's Conversations: Toward Harmless Data-Based Backdoor Attacks for Jailbreaking Large Language Models [69.11679786018206]
  Supervised fine-tuning (SFT) aligns large language models with human intent by training them on labeled task-specific data.<n>Recent studies have shown that malicious attackers can inject backdoors into these models by embedding triggers into the harmful question-answer pairs.<n>We propose a novel clean-data backdoor attack for jailbreaking LLMs.
  arXiv  Detail & Related papers  (2025-05-23T08:13:59Z)
• Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation Systems [39.05753852489526]
  Existing adversarial attack methods typically exploit knowledge base poisoning to probe the vulnerabilities of RAG systems.<n>This paper uses reasoning process templates from R1-based RAG systems to wrap erroneous knowledge into adversarial documents, and injects them into the knowledge base to attack RAG systems.<n>The key idea of our approach is that adversarial documents, by simulating the chain-of-thought patterns aligned with the model's training signals, may be misinterpreted by the model as authentic historical reasoning processes.
  arXiv  Detail & Related papers  (2025-05-22T08:22:46Z)
• POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models [4.620537391830117]
  Large language models (LLMs) are susceptible to hallucinations, which can lead to incorrect or misleading outputs.<n>Retrieval-augmented generation (RAG) is a promising approach to mitigate hallucinations by leveraging external knowledge sources.<n>In this paper, we study a poisoning attack on RAG systems named POISONCRAFT, which can mislead the model to refer to fraudulent websites.
  arXiv  Detail & Related papers  (2025-05-10T09:36:28Z)
• Hoist with His Own Petard: Inducing Guardrails to Facilitate Denial-of-Service Attacks on Retrieval-Augmented Generation of LLMs [8.09404178079053]
  Retrieval-Augmented Generation (RAG) integrates Large Language Models (LLMs) with external knowledge bases, improving output quality while introducing new security risks.<n>Existing studies on RAG vulnerabilities typically focus on exploiting the retrieval mechanism to inject erroneous knowledge or malicious texts, inducing incorrect outputs.<n>In this paper, we uncover a novel vulnerability: the safety guardrails of LLMs, while designed for protection, can also be exploited as an attack vector by adversaries. Building on this vulnerability, we propose MutedRAG, a novel denial-of-service attack that reversely leverages the guardrails to undermine the availability of
  arXiv  Detail & Related papers  (2025-04-30T14:18:11Z)
• Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models [0.0]
  Retrieval Augmented Generation (RAG) addresses this issue by combining Large Language Models with up-to-date information retrieval. This paper investigates prompt injection attacks on RAG, focusing on malicious objectives beyond misinformation. We build upon existing corpus poisoning techniques and propose a novel backdoor attack aimed at the fine-tuning process of the dense retriever component.
  arXiv  Detail & Related papers  (2024-10-18T14:02:34Z)
• Corpus Poisoning via Approximate Greedy Gradient Descent [48.5847914481222]
  We propose Approximate Greedy Gradient Descent, a new attack on dense retrieval systems based on the widely used HotFlip method for generating adversarial passages. We show that our method achieves a high attack success rate on several datasets and using several retrievers, and can generalize to unseen queries and new domains.
  arXiv  Detail & Related papers  (2024-06-07T17:02:35Z)

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.