Privacy-Utility Trade-offs in Neural Networks for Medical Population Graphs: Insights from Differential Privacy and Graph Structure. (arXiv:2307.06760v1 [cs.LG])

We initiate an empirical investigation into differentially private graph
neural networks on population graphs from the medical domain by examining
privacy-utility trade-offs at different privacy levels on both real-world and
synthetic datasets and performing auditing through membership inference
attacks. Our findings highlight the potential and the challenges of this
specific DP application area. Moreover, we find evidence that the underlying
graph structure constitutes a potential factor for larger performance gaps by
showing a correlation between the degree of graph homophily …

attacks auditing datasets differential privacy domain findings graphs insights investigation medical networks neural networks performing privacy private synthetic trade utility world