SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning

• URL: http://arxiv.org/abs/2605.28074v1
• Date: Wed, 27 May 2026 07:30:30 GMT
• Title: SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning
• Abstract summary: We present SilentRetrieval, a two-stage data poisoning attack that hijacks RAG systems through adversarially crafted documents.<n>SilentRetrieval achieves 84.6%/81.3% HR@10 and 57.5%/54.8% ASR-LLM on Natural Questions and MS MARCO, while maintaining near-benign perplexity.
• Score: 1.0998907972211756
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning attack that hijacks RAG systems through adversarially crafted yet fluent documents. Stage 1 uses Coordinated Beam Search, a multi-token joint optimization method with a fluency-similarity objective, to keep a poisoned host document retrievable while constraining perplexity. Stage 2 uses Context-Adaptive Trigger Generation, a lightweight trigger-fusion step driven by a frozen LLM, to integrate manipulation triggers into document content. Under a one-poisoned-document-per-query evaluation with synthetic target answers, SilentRetrieval achieves 84.6%/81.3% HR@10 and 57.5%/54.8% ASR-LLM on Natural Questions and MS MARCO, while maintaining near-benign perplexity. Cross-model evaluation across four target LLMs shows nontrivial effectiveness under a fixed trigger generator, and transfer tests against unseen retrievers, including ColBERT and commercial embedding models, yield 64.7% average HR@10 under the same injected-corpus protocol. In a sampled Wikipedia-scale evaluation, SilentRetrieval retains 74.2% HR@10 at a 0.016% poisoning ratio. Combined retrieval-side and generation-side defenses reduce attack success substantially but incur a latency trade-off. Human evaluation shows substantially lower flag rates than disfluent baselines, while remaining numerically more suspicious than benign content at the current sample size.

Related papers

• ToxicRAG: Compromising Retrieval-Augmented Generation Systems via Single-Shot Knowledge Poisoning Attacks [8.253108030536895]
  Representative attacks use multiple injected documents or templates that directly assert a target answer.<n>We present ToxicRAG, a one-document-per-target attack that expresses misinformation as a coherent knowledge-update narrative.<n>We evaluate the attack on 100 target questions from each of Natural Questions, HotpotQA, and MS-MARCO.
  arXiv  Detail & Related papers  (2026-09-10T04:42:21Z)
• 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)
• Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems [1.7327102304628392]
  Retrieval-Augmented Generation (RAG) grounds Large Language Model (LLM) outputs in external knowledge.<n>We propose an Evaluation Agent that combines Natural Language Inference (NLI) factual verification, a five-signal poison detector with relevance-weighted aggregation, and a Trust Index T = 0.4 F + 0.35 C + 0.25 (1 - P )<n>On TruthfulQA with Llama 3.3 70B, the agent reaches 91% accuracy and 100% precision, with 100% recall on instruction injection.
  arXiv  Detail & Related papers  (2026-08-21T13:42:41Z)
• Defending Retrieval-Augmented Intrusion Detection Against Knowledge Poisoning and Prompt Injection [0.0]
  We present RAG-IDS, a three-tier multi-agent intrusion detection framework with a retrieval-boundary defense.<n>Under prompt injection, multi-document retrieval limits label-flip success to 0.6-2.4%, compared with 35-55% for single-document retrieval.
  arXiv  Detail & Related papers  (2026-08-08T12:29:47Z)
• DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection [45.67420390185547]
  We propose PromptFuzz-SC, a semantic-character dual-space mutation framework for evaluating robustness against prompt injection.<n>A hybrid search strategy combining epsilon-greedy exploration and hill-climbing refinement is adopted to efficiently discover high-quality adversarial prompts.<n> Experimental results on DeepSeek demonstrate that dual-space mutation achieves the strongest overall attack performance.
  arXiv  Detail & Related papers  (2026-04-14T10:20:15Z)
• AdversarialCoT: Single-Document Retrieval Poisoning for LLM Reasoning [115.3243260783674]
  Retrieval-augmented generation (RAG) enhances large language model (LLM) reasoning by retrieving external documents.<n>We study knowledge-base poisoning attacks in RAG, where an attacker injects malicious content into the retrieval corpus.<n>We propose AdversarialCoT, a query-specific attack that poisons only a single document in the corpus.
  arXiv  Detail & Related papers  (2026-04-14T02:10:23Z)
• StutterFuse: Mitigating Modality Collapse in Stuttering Detection with Jaccard-Weighted Metric Learning and Gated Fusion [0.40105987447353786]
  Stuttering detection breaks down when disfluencies overlap.<n>Existing parametric models struggle to distinguish complex, simultaneous disfluencies.<n>We introduce StutterFuse, the first Retrieval-Augmented generalization (RAC) for multi-label detection.
  arXiv  Detail & Related papers  (2025-12-15T18:28:39Z)
• Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs [54.90315421117162]
  We propose a novel poisoning method via completely harmless data.<n>Inspired by the causal reasoning in auto-regressive LLMs, we aim to establish robust associations between triggers and an affirmative response prefix.<n>We observe an interesting resistance phenomenon where the LLM initially appears to agree but subsequently refuses to answer.
  arXiv  Detail & Related papers  (2025-05-23T08:13:59Z)
• LLM Robustness Against Misinformation in Biomedical Question Answering [50.98256373698759]
  The retrieval-augmented generation (RAG) approach is used to reduce the confabulation of large language models (LLMs) for question answering. We evaluate the effectiveness and robustness of four LLMs against misinformation in answering biomedical questions.
  arXiv  Detail & Related papers  (2024-10-27T16:23:26Z)
• Efficient Trigger Word Insertion [9.257916713112945]
  Our main objective is to reduce the number of poisoned samples while still achieving a satisfactory Attack Success Rate (ASR) in text backdoor attacks. We propose an efficient trigger word insertion strategy in terms of trigger word optimization and poisoned sample selection. Our approach achieves an ASR of over 90% with only 10 poisoned samples in the dirty-label setting and requires merely 1.5% of the training data in the clean-label setting.
  arXiv  Detail & Related papers  (2023-11-23T12:15:56Z)
• ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks [91.55895047448249]
  This paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases. We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets. Our generated data is human-readable and useful to trigger hallucination in large language models.
  arXiv  Detail & Related papers  (2023-10-19T06:37:32Z)
• A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection [63.56136319976554]
  Large Language Models (LLMs) generate hallucinations, which can cause significant damage when deployed for mission-critical tasks. We propose a self-check approach based on reverse validation to detect factual errors automatically in a zero-resource fashion. We empirically evaluate our method and existing zero-resource detection methods on two datasets.
  arXiv  Detail & Related papers  (2023-10-10T10:14:59Z)
• Elastic Weight Removal for Faithful and Abstractive Dialogue Generation [61.40951756070646]
  A dialogue system should generate responses that are faithful to the knowledge contained in relevant documents. Many models generate hallucinated responses instead that contradict it or contain unverifiable information. We show that our method can be extended to simultaneously discourage hallucinations and extractive responses.
  arXiv  Detail & Related papers  (2023-03-30T17:40:30Z)

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.