mlsanityData to 14 Oct 2026

GraphRAG-LTM: A Layered Threat Modeling Framework for Attacks on Graph Retrieval-Augmented Generation

arXiv 2610.19549 ↗First posted 14 Oct 2026cs.CLcited by 0

On the map: Retrieval-augmented generation → Privacy and security of RAG

Abstract (arXiv)

Graph retrieval-augmented generation (GraphRAG) uses document-derived knowledge graphs to assemble evidence for large language model (LLM) answers. Its security depends on both the seed chunks retrieved for a query and the graph evidence assembled from them, yet attacks on this evidence path remain underexplored. We introduce GraphRAG-LTM, a Layered Threat Modeling framework that tests three nested levels of attacker access. BB Query uses ranking feedback to make query edits under a semantic-similarity constraint and demote relevant seed chunks. WB Query uses retriever gradients for the same objective. Graph-aware WB keeps the white-box adversarial query and deletes bridge triplets from the query-specific evidence graph, disrupting multi-hop evidence propagation through localized graph edits. Across datasets, retrievers, and LLM backbones, rank feedback alone reduces answer quality, gradient access strengthens query attacks, and bridge-triplet deletion further impairs supporting-fact retrieval. Further analyses show how seed retrieval and graph evidence jointly contribute to these failures.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 29 of its 43 references that are in the map. First posted on arXiv 14 Oct 2026.

Builds on

29 of 43 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimization10 Apr

Other references · 28

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  6. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  7. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
  8. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  9. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  10. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  11. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 832
  12. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
16 more
  1. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 722
  2. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 671
  3. 2023Prompt Injection attack against LLM-integrated Applicationscited by 605
  4. 2019Evaluating the Factual Consistency of Abstractive Text Summarizationcited by 584
  5. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 578
  6. 2023NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Railscited by 365
  7. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 281
  8. 2023Poisoning Retrieval Corpora by Injecting Adversarial Passagescited by 159
  9. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 152
  10. 2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphscited by 119
  11. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 116
  12. 2024Rule Based Rewards for Language Model Safetycited by 108
  13. 2024RaFe: Ranking Feedback Improves Query Rewriting for RAGcited by 49
  14. 2023Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuningcited by 29
  15. 2024InterrogateLLM: Zero-Resource Hallucination Detection in LLM-Generated Answerscited by 27
  16. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Levelcited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025GraphRAG under Fire
  2. 2025A Few Words Can Distort Graphs: Knowledge Poisoning Attacks on Graph-based Retrieval-Augmented Generation of Large Language Models
  3. 2026LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation
  4. 2026Graphs Don't Stay Secret: Practical Subgraph Reconstruction Attacks on Defended Graph RAG
  5. 2026Toward Robust GraphRAG: Mitigating Retrieval Drift and Hallucination from Imperfect Knowledge Graphs
  6. 2026Retrieval Pivot Attacks in Hybrid RAG: Measuring and Mitigating Amplified Leakage from Vector Seeds to Graph Expansion
  7. 2025GRADA: Graph-based Reranking against Adversarial Documents Attack
  8. 2026TRIS: A Tri-Layer Retrieval Integrity Sieve Against Knowledge Poisoning