Empirical Auditing of Edge-Private Graph Generators
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 23 references that are in the map. First posted on arXiv 21 Sep 2026.
Builds on
11 of 23 references.
References · 11
- 2020Auditing Differentially Private Machine Learning: How Private is Private SGD?cited by 218
- 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 199
- 2017Cooperative Game Theory Approaches for Network Partitioningcited by 135
- 2020Stealing Links from Graph Neural Networkscited by 115
- 2022TAPAS: a Toolbox for Adversarial Privacy Auditing of Synthetic Datacited by 57
- 2020A Comprehensive Survey on Local Differential Privacy Toward Data Statistics and Analysiscited by 26
- 2021Private Graph Data Release: A Surveycited by 15
- 2023PrivGraph: Differentially Private Graph Data Publication by Exploiting Community Informationcited by 13
- 2021Online Learning of Network Bottlenecks via Minimax Pathscited by 9
- 2014Differentially Private Exponential Random Graphscited by 7
- 2024PGB: Benchmarking Differentially Private Synthetic Graph Generation Algorithmscited by 2
Built on by
Not cited yet.