AntTech

May 4, 2023 · Artificial Intelligence

Privacy Risks and Differentially Private Defense for Federated Knowledge Graph Representation Learning

This paper investigates the privacy leakage risks of federated knowledge graph representation learning, designs three membership inference attacks to quantify the threats, and proposes DP‑Flames, a differential‑privacy‑based defense that leverages gradient sparsity to achieve a favorable privacy‑utility trade‑off.