Poincar\'e Differential Privacy for Hierarchy-Aware Graph Embedding

arXiv:2312.12183v3 Announce Type: replace-cross
Abstract: Hierarchy is an important and commonly observed topological property in real-world graphs that indicate the relationships between supervisors and subordinates or the organizational behavior of human groups. As hierarchy is introduced as a new inductive bias into the Graph Neural Networks (GNNs) in various tasks, it implies latent topological relations for attackers to improve their inference attack performance, leading to serious privacy leakage issues. In addition, existing privacy-preserving frameworks suffer from reduced protection ability in …

arxiv aware bias cs.cr cs.lg differential privacy graph graphs hierarchy human important networks neural networks privacy property real relationships world