Tracing Target Answers in Poisoned Retrieval Corpora via Token Influence Attribution

• URL: http://arxiv.org/abs/2606.25721v1
• Date: Wed, 24 Jun 2026 11:39:26 GMT
• Title: Tracing Target Answers in Poisoned Retrieval Corpora via Token Influence Attribution
• Abstract summary: TRACE identifies poisoning attacks by tracing answer-related tokens through token influence attribution.<n>TRACE first discovers recurrent high-influence keywords across retrieved documents and then performs a secondary verification to confirm their influence on model predictions.
• Score: 45.91389330863296
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate model outputs through malicious retrieved documents. Existing detection methods typically rely on auxiliary classifiers or additional LLM-based verification, introducing substantial computational overhead. We present TRACE, a lightweight detection framework that identifies poisoning attacks by tracing answer-related tokens through token influence attribution. TRACE first discovers recurrent high-influence keywords across retrieved documents and then performs a secondary verification to confirm their influence on model predictions. Experiments on three QA benchmarks and six LLMs demonstrate strong detection performance while simultaneously uncovering attacker-specified target answers.

Related papers

• 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)
• When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse [34.49107596901488]
  RAGs are increasingly susceptible to poisoning attacks, in which adversarial documents are injected to manipulate generator outputs.<n>Previous methods rely on output-side signals such as perplexity and consistency checks to detect such attacks.<n>We propose textttD-SCAN, a lightweight detection framework that monitors attention dynamics to identify attacked generations.
  arXiv  Detail & Related papers  (2026-08-07T08:23:26Z)
• Attention Hijacking: Response Manipulation Across Queries in Vision-Language Models [57.870323273127234]
  Motivated by the observation, we propose textbfAttention Hijacking, a novel adversarial attack that steers internal attention toward a persistent image-dominant pattern.<n>Our method reduces the dependence of the manipulated output on the specific wording of the query.
  arXiv  Detail & Related papers  (2026-05-17T08:02:27Z)
• Needle-in-RAG: Prompt-Conditioned Character-Level Traceback of Poisoned Spans in Retrieved Evidence [4.039934762896615]
  RAGCharacter is a two-pass forensic framework that localizes the responsible retrieved span for a concrete misgeneration event.<n>We study black-box character-level poison traceback in RAG and present RAGCharacter, a two-pass forensic framework that localizes the responsible retrieved span for a concrete misgeneration event.
  arXiv  Detail & Related papers  (2026-05-03T08:42:29Z)
• 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)
• 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)
• Stealthy LLM-Driven Data Poisoning Attacks Against Embedding-Based Retrieval-Augmented Recommender Systems [16.79952669254101]
  We study provider-side data poisoning in retrieval-augmented recommender systems (RAG)<n>By modifying only a small fraction of tokens within item descriptions, an attacker can significantly promote or demote targeted items.<n>Experiments on MovieLens, using two large language model (LLM) retrieval modules, show that even subtle attacks shift final rankings and item exposures while eluding naive detection.
  arXiv  Detail & Related papers  (2025-05-08T12:53:42Z)
• RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis [7.846936346897295]
  RevPRAG is a flexible and automated detection pipeline that leverages the activations of LLMs for poisoned response detection.<n>Our results on multiple benchmark datasets and RAG architectures show our approach could achieve 98% true positive rate, while maintaining false positive rates close to 1%.
  arXiv  Detail & Related papers  (2024-11-28T06:29:46Z)
• Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information [67.78183175605761]
  Large Language Models are susceptible to adversarial prompt attacks. This vulnerability underscores a significant concern regarding the robustness and reliability of LLMs. We introduce a novel approach to detecting adversarial prompts at a token level.
  arXiv  Detail & Related papers  (2023-11-20T03:17:21Z)
• Exploring Model Dynamics for Accumulative Poisoning Discovery [62.08553134316483]
  We propose a novel information measure, namely, Memorization Discrepancy, to explore the defense via the model-level information. By implicitly transferring the changes in the data manipulation to that in the model outputs, Memorization Discrepancy can discover the imperceptible poison samples. We thoroughly explore its properties and propose Discrepancy-aware Sample Correction (DSC) to defend against accumulative poisoning attacks.
  arXiv  Detail & Related papers  (2023-06-06T14:45:24Z)
• Detection of Adversarial Supports in Few-shot Classifiers Using Feature Preserving Autoencoders and Self-Similarity [89.26308254637702]
  We propose a detection strategy to highlight adversarial support sets. We make use of feature preserving autoencoder filtering and also the concept of self-similarity of a support set to perform this detection. Our method is attack-agnostic and also the first to explore detection for few-shot classifiers to the best of our knowledge.
  arXiv  Detail & Related papers  (2020-12-09T14:13:41Z)

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.