Metraipolis › archive › dc_bd5389d3e293

Differentially Private GraphRAG: Protecting Relation Connectivity and Semantics — arXiv:2611.09658

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09658
License (as archived)
CC0-1.0
Archived
2026-11-09T22:35:10.616Z
SHA-256 of the archived text
0bf07bd72e7936f831681ee87d89a9be24f19407046da3be89b38f1b1864ac35
Stable URL of this page
https://metraipolis.com/documento/dc_bd5389d3e293

How to cite

Differentially Private GraphRAG: Protecting Relation Connectivity and Semantics — arXiv:2611.09658 — arXiv (en), https://arxiv.org/abs/2611.09658 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd5389d3e293 (Metraipolis archive dc_bd5389d3e293, sha256 0bf07bd72e7936f831681ee87d89a9be24f19407046da3be89b38f1b1864ac35)
BibTeX
@misc{dcbd5389d3e293,
  title = {Differentially Private GraphRAG: Protecting Relation Connectivity and Semantics — arXiv:2611.09658},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09658},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd5389d3e293; sha256 0bf07bd72e7936f831681ee87d89a9be24f19407046da3be89b38f1b1864ac35},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09658. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Graph Retrieval-Augmented Generation (GraphRAG) connects information across documents through entity relationships to support relational reasoning. However, black-box access to GraphRAG systems can enable adversaries to reconstruct knowledge graphs and recover both structural connectivity between entities and the semantics of their relationships. Existing defenses lack formal privacy guarantees and provide limited protection against such reconstruction attacks. We propose RelGuard, the first differentially private framework for GraphRAG, which provides formal privacy guarantees by mitigating connectivity leakage and protecting relations and their semantic meaning through relation removal. We formalize relation differential privacy (relation-DP), which bounds the distinguishability of mechanism outputs according to the semantic distance between alternative relations while accounting for relation removal. Building on this definition, we develop a four-step defense mechanism that sanitizes source documents before GraphRAG indexing by perturbing relation predicates or removing their associated connectivity using the exponential mechanism. Experiments across three GraphRAG systems and two targeted reconstruction attacks demonstrate that RelGuard provides stronger protection against reconstruction attacks than four existing defense mechanisms while better preserving downstream utility.

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/2611.09658 — 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 2026-11-09T22:30:47.338Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).