Heterogeneous Randomized Response for Differential Privacy in Graph Neural Networks. (arXiv:2211.05766v1 [cs.LG])

Graph neural networks (GNNs) are susceptible to privacy inference attacks
(PIAs), given their ability to learn joint representation from features and
edges among nodes in graph data. To prevent privacy leakages in GNNs, we
propose a novel heterogeneous randomized response (HeteroRR) mechanism to
protect nodes' features and edges against PIAs under differential privacy (DP)
guarantees without an undue cost of data and model utility in training GNNs.
Our idea is to balance the importance and sensitivity of nodes' features and …

differential privacy networks neural networks privacy response