Live intelligence

Latest AI updates

1 updates
Research Editor selected

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.

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

GraphRAGdifferential privacyprivacy attacks