Link Stealing Attacks Against Inductive Graph Neural Networks

arXiv:2405.05784v1 Announce Type: cross
Abstract: A graph neural network (GNN) is a type of neural network that is specifically designed to process graph-structured data. Typically, GNNs can be implemented in two settings, including the transductive setting and the inductive setting. In the transductive setting, the trained model can only predict the labels of nodes that were observed at the training time. In the inductive setting, the trained model can be generalized to new nodes/graphs. Due to its flexibility, the inductive …

abstract arxiv attacks cs.cr cs.lg data gnn gnns graph graph neural network graph neural networks inductive labels network networks neural network neural networks process stealing structured data type