Faculty, Staff and Student Publications
Language
English
Publication Date
10-1-2024
Journal
Conference: Computer and Communications Security
DOI
10.1145/3658644.3670351
PMID
40642521
PMCID
PMC12241667
PubMedCentral® Posted Date
7-10-2025
PubMedCentral® Full Text Version
Author MSS
Abstract
Federated learning (FL) enhanced by differential privacy has emerged as a popular approach to better safeguard the privacy of client-side data by protecting clients’ contributions during the training process. Existing solutions typically assume a uniform privacy budget for all records and provide one-size-fits-all solutions that may not be adequate to meet each record’s privacy requirement. In this paper, we explore the uncharted territory of cross-silo FL with record-level personalized differential privacy. We devise a novel framework named rPDP-FL, employing a two-stage hybrid sampling scheme with both uniform client-level sampling and non-uniform record-level sampling to accommodate varying privacy requirements.
A critical and non-trivial problem is how to determine the ideal per-record sampling probability 𝑞given the personalized privacy budget 𝜀. We introduce a versatile solution named Simulation-CurveFitting, allowing us to uncover a significant insight into the nonlinear correlation between𝑞 and𝜀 and derive an elegant mathematical model to tackle the problem. Our evaluation demonstrates that our solution can provide significant performance gains over the baselines that do not consider personalized privacy preservation.
Keywords
Federated Learning, Differential Privacy, Personalized Privacy Protection
Published Open-Access
yes
Recommended Citation
Liu, Junxu; Lou, Jian; Xiong, Li; et al., "Cross-silo Federated Learning with Record-level Personalized Differential Privacy" (2024). Faculty, Staff and Student Publications. 924.
https://digitalcommons.library.tmc.edu/uthshis_docs/924