Differential Privacy in HyperNetworks for Personalized Federated Learning

Vaisnavi Nemala, Phung Lai, Nhat Hai Phan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publicationCIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery
Pages4224-4228
Number of pages5
ISBN (Electronic)9798400701245
DOIs
StatePublished - Oct 21 2023
Event32nd ACM International Conference on Information and Knowledge Management, CIKM 2023 - Birmingham, United Kingdom
Duration: Oct 21 2023Oct 25 2023

Publication series

NameInternational Conference on Information and Knowledge Management, Proceedings

Conference

Conference32nd ACM International Conference on Information and Knowledge Management, CIKM 2023
Country/TerritoryUnited Kingdom
CityBirmingham
Period10/21/2310/25/23

All Science Journal Classification (ASJC) codes

  • General Business, Management and Accounting
  • General Decision Sciences

Keywords

  • Differential Privacy
  • Federated Learning
  • Hypernetworks

Fingerprint

Dive into the research topics of 'Differential Privacy in HyperNetworks for Personalized Federated Learning'. Together they form a unique fingerprint.

Cite this