Back to AI News
arxiv

RelGuard: First Differentially Private Framework for GraphRAG

Researchers propose RelGuard, the first differentially private framework for GraphRAG, offering formal privacy guarantees against knowledge graph reconstruction attacks. It introduces relation differential privacy (relation-DP) and a four-step defense that sanitizes documents by perturbing or removing relation predicates. Experiments show stronger protection than four existing defenses while preserving utility.

AI Brief

This is a novel research contribution addressing a critical privacy gap in GraphRAG, with formal guarantees and empirical validation.

arXiv:2611.09658v1 Announce Type: cross Abstract: 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.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!