Privacy-Utility Trade-Off in Federated Learning

Kai Li (), Xin Yuan () and Wei Ni ()
Additional contact information
Kai Li: University of Luxembourg, Interdisciplinary Centre for Security, Reliability and Trust (SnT)
Xin Yuan: Commonwealth Scientific and Industrial Research Organisation (CSIRO), Data61 Business Unit
Wei Ni: Commonwealth Scientific and Industrial Research Organisation (CSIRO), Data61 Business Unit

Chapter 9 in Security and Resilience in Distributed Machine Learning, 2026, pp 177-207 from Springer

Abstract: Abstract While preserving the privacy of FL, DP inevitably degrades the utility (i.e., accuracy) of FL due to model perturbations caused by DP noise added to model updates [11]. Existing studies have considered exclusively noise with a persistent root-mean-square amplitude and overlooked an opportunity to adjust the amplitudes to alleviate the adverse effects of the noise. This chapter presents a new DP perturbation mechanism with a time-varying noise amplitude to protect the privacy of FL and retain the capability of adjusting the learning performance.

Date: 2026
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:ssrchp:978-3-032-23959-4_9

Ordering information: This item can be ordered from
http://www.springer.com/9783032239594

DOI: 10.1007/978-3-032-23959-4_9

Access Statistics for this chapter

More chapters in Springer Series in Reliability Engineering from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().