Privacy Assessment of Federated Learning using Private Personalized Layers

Abstract

Federated Learning (FL) is a collaborative scheme to train a learning model across multiple participants without sharing data. While FL is a clear step forward towards enforcing users' privacy, different inference attacks have been developed. In this paper, we quantify the utility and privacy trade-off of a FL scheme using private personalized layers. While this scheme has been proposed as local adaptation to improve the accuracy of the model through local personalization, it has also the advantage to minimize the information about the model exchanged with the server. However, the privacy of such a scheme has never been quantified. Our evaluations using motion sensor dataset show that personalized layers speed up the convergence of the model and slightly improve the accuracy for all users compared to a standard FL scheme while better preventing both attribute and membership inferences compared to a FL scheme using local differential privacy.

References in corpus (7)

• Federated Learning: Challenges, Methods, and Future Directions
• Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• How To Backdoor Federated Learning
• Federated Learning with Personalization Layers
• Mobile Sensor Data Anonymization
• Salvaging Federated Learning by Local Adaptation
• The Trade-Offs of Private Prediction