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
Recommended Citation
Nemala, Vaisnavi; Lai, Phung; and Phan, Nhat Hai, "Differential Privacy in HyperNetworks for Personalized Federated Learning" (2023). Faculty Publications. 1375.
https://digitalcommons.njit.edu/fac_pubs/1375