SOURCE-LINKED INTELLIGENCE

Empirical Auditing of Edge-Private Graph Generators

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

We empirically audit privacy leakage by testing whether outputs from edge-neighbouring inputs remain distinguishable, using statistically valid lower bounds on the privacy loss witnessed by our attacks. Our framework compares direct-edge, local-structural, and GNN-based attacks through the geometry surrounding a target edge. Experiments across two generators and two networks show that privacy leakage is both mechanism- and network-dependent, with learned representations revealing information not captured by conventional local statistics.

Read original source ↗ Open in workspace

recordType

paper

region

Global