Federated Learning with Local Differential Privacy: Trade-Offs between Privacy, Utility, and Communication

Muah Kim, Onur G¨unl¨u, Rafael F. Schaefer

Research output: Contribution to journalConference articlepeer-review

87 Scopus citations

Abstract

Federated learning (FL) allows to train a massive amount of data privately due to its decentralized structure. Stochastic gradient descent (SGD) is commonly used for FL due to its good empirical performance, but sensitive user information can still be inferred from weight updates shared during FL iterations. We consider Gaussian mechanisms to preserve local differential privacy (LDP) of user data in the FL model with SGD. The trade-offs between user privacy, global utility, and transmission rate are proved by defining appropriate metrics for FL with LDP. Compared to existing results, the query sensitivity used in LDP is defined as a variable, and a tighter privacy accounting method is applied. The proposed utility bound allows heterogeneous parameters over all users. Our bounds characterize how much utility decreases and transmission rate increases if a stronger privacy regime is targeted. Furthermore, given a target privacy level, our results guarantee a significantly larger utility and a smaller transmission rate as compared to existing privacy accounting methods.

Original languageEnglish
Pages (from-to)2650-2654
Number of pages5
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2021-June
DOIs
StatePublished - 2021
Externally publishedYes
Event2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada
Duration: 6 Jun 202111 Jun 2021

Keywords

  • Composition theorems
  • Federated learning (fl)
  • Gaussian randomization
  • Local differential privacy (ldp)
  • Stochastic gradient descent (sgd)

Fingerprint

Dive into the research topics of 'Federated Learning with Local Differential Privacy: Trade-Offs between Privacy, Utility, and Communication'. Together they form a unique fingerprint.

Cite this