Differential Privacy in HyperNetworks for Personalized Federated Learning

Document Type

Conference Proceeding

Publication Date

10-21-2023

Abstract

Federated learning (FL) is a framework for collaborative learning among users through a coordinating server. A recent HyperNetwork-based personalized FL framework, called HyperNetFL, is used to generate local models using personalized descriptors optimized for each user independently. However, HyperNetFL introduces unknown privacy risks. This paper introduces a novel approach to preserve user-level differential privacy, dubbed User-level DP, by providing formal privacy protection for data owners in training a HyperNetFL model. To achieve that, our proposed algorithm, called UDP-Alg, optimizes the trade-off between privacy loss and model utility by tightening sensitivity bounds. An intensive evaluation using benchmark datasets shows that our proposed UDP-Alg significantly improves privacy protection at a modest cost in utility.

Identifier

85178152945 (Scopus)

ISBN

[9798400701245]

Publication Title

International Conference on Information and Knowledge Management Proceedings

External Full Text Location

https://doi.org/10.1145/3583780.3615203

First Page

4224

Last Page

4228

Grant

IIS-2041096

Fund Ref

National Science Foundation

This document is currently not available here.

Share

COinS