Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding

Abstract

Knowledge Graph Embedding (KGE) is a fundamental technique that extracts expressive representation from knowledge graph (KG) to facilitate diverse downstream tasks. The emerging federated KGE (FKGE) collaboratively trains from distributed KGs held among clients while avoiding exchanging clients' sensitive raw KGs, which can still suffer from privacy threats as evidenced in other federated model trainings (e.g., neural networks). However, quantifying and defending against such privacy threats remain unexplored for FKGE which possesses unique properties not shared by previously studied models. In this paper, we conduct the first holistic study of the privacy threat on FKGE from both attack and defense perspectives. For the attack, we quantify the privacy threat by proposing three new inference attacks, which reveal substantial privacy risk by successfully inferring the existence of the KG triple from victim clients. For the defense, we propose DP-Flames, a novel differentially private FKGE with private selection, which offers a better privacy-utility tradeoff by exploiting the entity-binding sparse gradient property of FKGE and comes with a tight privacy accountant by incorporating the state-of-the-art private selection technique. We further propose an adaptive privacy budget allocation policy to dynamically adjust defense magnitude across the training procedure. Comprehensive evaluations demonstrate that the proposed defense can successfully mitigate the privacy threat by effectively reducing the success rate of inference attacks from 83.1% to 59.4% on average with only a modest utility decrease.

Vaccine Coverage and Effectiveness in a School-Based Varicella Outbreak in Jinan Prefecture, Shandong Province

“…The study of federated KG embedding has attracted attention due to privacy protection and other needs. Hu et al [5] conducted the first comprehensive study of privacy threats in emerging federated KG embedding from attack and defence perspectives. Compared to traditional KG embedding research, federated KG embedding is trained collaboratively from distributed KGs held between clients, avoiding the leakage and interaction of sensitive information in the original KGs of clients.…”

“…KG embedding maps entities and relationships into vector space, effectively encoding structural and semantic information for link prediction [3] and other downstream applications [4]. Federated KG embedding learning [5] [6] [7] extends this approach to decentralized environments, enabling collaborative model training across distributed data sources while preserving data privacy.…”