Edge Private Graph Neural Networks with Singular Value Perturbation

arXiv:2403.10995v1 Announce Type: new
Abstract: Graph neural networks (GNNs) play a key role in learning representations from graph-structured data and are demonstrated to be useful in many applications. However, the GNN training pipeline has been shown to be vulnerable to node feature leakage and edge extraction attacks. This paper investigates a scenario where an attacker aims to recover private edge information from a trained GNN model. Previous studies have employed differential privacy (DP) to add noise directly to the adjacency …

abstract applications arxiv attacks cs.ai cs.cr cs.lg cs.si data edge extraction feature gnn gnns graph graph neural networks however key networks neural networks node paper pipeline role singular structured data training training pipeline type value vulnerable