mlsanityData to 14 Oct 2026

Hop-Decayed Influence: New Vulnerabilities of Structural Auxiliary Indexing in GraphRAG Pipelines with LLM

arXiv 2610.02373 ↗First posted 1 Oct 2026cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

GraphRAG pipelines construct auxiliary structures during offline indexing--semantic summaries, hierarchical edges, and pre-computed scores--that determine how retrieval is prioritised at query time. Prior attacks target only instance-level components (nodes, edges, triples), overlooking these schema-level structures. We formalise Auxiliary Schema-Level Entity as a novel attack surface and propose the 3S Framework (Semantics, Structure, Scoring) for its systematic exploitation. Our Hop-Decayed Influence (HDI) attack identifies high-impact targets through query-aware influence propagation and corrupts their auxiliary structures post-indexing. Across two benchmarks (HotpotQA, 2WikiMultiHopQA) and two architectures (Microsoft GraphRAG, HippoRAG2), HDI achieves 88-94% attack success rate while modifying as few as 0.016% of auxiliary structures. Each modification affects up to 6.00 queries (Schema Leverage Ratio), demonstrating 1:N amplification unavailable to instance-level attacks. Manipulated structures evade perplexity and paraphrase defenses with over 99% evasion rate, as they remain linguistically coherent system-generated artifacts. These results reveal that auxiliary schema-level entities receive implicit trust without runtime validation, constituting a structural blind spot in current GraphRAG defenses. https://github.com/Jisung-Pacific/HDI-GraphRAG-Attack.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 34 references that are in the map. First posted on arXiv 1 Oct 2026.

Builds on

27 of 34 references.

References · 27

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  5. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  6. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  7. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  8. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 651
  9. 2023Catastrophic Jailbreak of Open-source LLMs via Exploiting Generationcited by 451
  10. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
  11. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 281
  12. 2024PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Modelscited by 267
15 more
  1. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 231
  2. 2024G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answeringcited by 223
  3. 2025Why Language Models Hallucinatecited by 220
  4. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
  5. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 88
  6. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generationcited by 80
  7. 2025Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learningcited by 52
  8. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 36
  9. 2025GraphRAG under Firecited by 24
  10. 2023QASiNa: Religious Domain Question Answering using Sirah Nabawiyahcited by 15
  11. 2025Exposing Privacy Risks in Graph Retrieval-Augmented Generationcited by 5
  12. 2025A Few Words Can Distort Graphs: Knowledge Poisoning Attacks on Graph-based Retrieval-Augmented Generation of Large Language Modelscited by 4
  13. 2025RAG Safety: Exploring Knowledge Poisoning Attacks to Retrieval-Augmented Generationcited by 3
  14. 2025DEMENTIA-PLAN: An Agent-Based Framework for Multi-Knowledge Graph Retrieval-Augmented Generation in Dementia Carecited by 2
  15. 2025How stealthy is stealthy? Studying the Efficacy of Black-Box Adversarial Attacks in the Real Worldcited by 1

Built on by

Not cited yet.