Metraipolis › archive › dc_70144688e008

Hop-Decayed Influence: New Vulnerabilities of Structural Auxiliary Indexing in GraphRAG Pipelines with LLM — arXiv:2610.02373

Source
arXiv
Original
https://arxiv.org/abs/2610.02373
License (as archived)
CC0-1.0
Archived
2026-10-05T22:49:57.032Z
SHA-256 of the archived text
200f7dc7462e0bb30c71b4cd79259a0e45a01ea65c459596431f0db974ef1aba
Stable URL of this page
https://metraipolis.com/documento/dc_70144688e008

How to cite

Hop-Decayed Influence: New Vulnerabilities of Structural Auxiliary Indexing in GraphRAG Pipelines with LLM — arXiv:2610.02373 — arXiv, https://arxiv.org/abs/2610.02373 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_70144688e008 (Metraipolis archive dc_70144688e008, sha256 200f7dc7462e0bb30c71b4cd79259a0e45a01ea65c459596431f0db974ef1aba)
BibTeX
@misc{dc70144688e008,
  title = {Hop-Decayed Influence: New Vulnerabilities of Structural Auxiliary Indexing in GraphRAG Pipelines with LLM — arXiv:2610.02373},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02373},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_70144688e008; sha256 200f7dc7462e0bb30c71b4cd79259a0e45a01ea65c459596431f0db974ef1aba},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02373. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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. this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.02373 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-05T22:45:55.744Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).