Pith. sign in

REVIEW 13 cited by

TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2501.00879 v3 pith:IFJVJGLQ submitted 2025-01-01 cs.CL

Huichi Zhou , Kin-Hei Lee , Zhonghao Zhan , Yue Chen , Zhenhao Li , Zhaoyang Wang , Hamed Haddadi , Emine Yilmaz This is my paper
classification cs.CL
keywords trustraggenerationllmsattackdetectemployslanguagemalicious
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user queries. These systems, however, remain susceptible to corpus poisoning attacks, which can severely impair the performance of LLMs. To address this challenge, we propose TrustRAG, a robust framework that systematically filters malicious and irrelevant content before it is retrieved for generation. Our approach employs a two-stage defense mechanism. The first stage implements a cluster filtering strategy to detect potential attack patterns. The second stage employs a self-assessment process that harnesses the internal capabilities of LLMs to detect malicious documents and resolve inconsistencies. TrustRAG provides a plug-and-play, training-free module that integrates seamlessly with any open- or closed-source language model. Extensive experiments demonstrate that TrustRAG delivers substantial improvements in retrieval accuracy, efficiency, and attack resistance.

Discussion (0). Sign in to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DenialRAG: Single-Document RAG Poisoning via Embedded Parametric Denial

    cs.CR 2026-08 conditional novelty 6.0 of 10

    A single poisoned document that explicitly names and refutes the correct answer can steer RAG systems toward attacker-chosen wrong answers, with effects that vary by target model.

  2. MIRAGE: Defending Long-Form RAG Against Misinformation Pollution

    cs.CL 2026-07 conditional novelty 6.0 of 10

    Cross-document NLI claim graphs plus a defended-claims gate restore long-form RAG factuality under mixed and fully polluted retrieval better than prior robust-RAG methods.

  3. Knowledge Base Poisoning Attacks and Defense for Policy-Aware LLM-RAG Framework

    cs.CR 2026-07 conditional novelty 6.0 of 10

    Query-agnostic KB poisoning corrupts 85% of IoBT LLM contexts from one rule; taxonomy-aware dual detection restores 100% integrity with 7 ms overhead.

  4. UniC-RAG: Universal Knowledge Corruption Attacks to Retrieval-Augmented Generation

    cs.CR 2025-08 conditional novelty 6.0 of 10

    A universal knowledge-corruption attack uses as few as 100 crafted texts to hijack responses to thousands of diverse user queries in retrieval-augmented generation.

  5. Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection

    cs.CL 2025-07 conditional novelty 6.0 of 10

    GMTP detects poisoned RAG documents by masking high-gradient tokens and flagging documents whose masked-token probabilities are abnormally low.

  6. RAG Safety: Exploring Knowledge Poisoning Attacks to Retrieval-Augmented Generation

    cs.CR 2025-07 conditional novelty 6.0 of 10

    Inserting a small number of crafted triples into a knowledge graph can flip KG-RAG question answering toward attacker-chosen incorrect answers across four recent systems.

  7. Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMs

    cs.LG 2025-06 reject novelty 6.0 of 10

    A retrieval-augmented generation system can be poisoned with reward-optimized biased documents and vector-space manipulation to substantially increase biased LLM outputs.

  8. TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation

    cs.CR 2026-07 conditional novelty 5.0 of 10

    A three-ring RAG defense cuts non-adaptive PoisonedRAG attack success from ~91% to ~13% on 10 questions over a 5,000-document Wikipedia base.

  9. Fact or Facsimile? Evaluating the Factual Robustness of Modern Retrievers

    cs.IR 2025-08 conditional novelty 5.0 of 10

    Retrievers and rerankers built from LLMs score near random on the FACTOR factuality benchmark, far below their base models, and fail when correct answers are paraphrased.

  10. REAL-IoT: Characterizing GNN Intrusion Detection Robustness under Practical Adversarial Attack

    cs.CR 2025-07 reject novelty 5.0 of 10

    GNN-based intrusion detectors show lower accuracy on REAL-IoT's merged datasets, but the paper's own tables are inconsistent and the drift protocol is not a true distribution-shift test.

  11. Benchmarking Poisoning Attacks against Retrieval-Augmented Generation

    cs.CR 2025-05 conditional novelty 5.0 of 10

    A unified benchmark evaluation finds that existing RAG poisoning attacks remain effective on standard QA datasets, drop on expanded knowledge bases, and are only partially mitigated by current defenses.

  12. Poster: Enhancing GNN Robustness for Network Intrusion Detection via Agent-based Analysis

    cs.CR 2025-06 conditional novelty 4.0 of 10

    LLM agents that filter suspicious nodes before a GNN classifier restore clean-level accuracy on a synthetic node injection attack.

  13. RAGtifier: Evaluating RAG Generation Approaches of State-of-the-Art RAG Systems for the SIGIR LiveRAG Competition

    cs.IR 2025-06 conditional novelty 4.0 of 10

    A RAG pipeline using InstructRAG, Pinecone, and BGE placed third in the 2025 LiveRAG Challenge, though internal evaluation only weakly predicted official scores.

Pith tools