Strategic Data Revocation in Federated Unlearning

Ningning Ding*, Ermin Wei, Randall Berry

*Corresponding author for this work

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

2 Scopus citations

Abstract

By allowing users to erase their data's impact on federated learning models, federated unlearning protects users' right to be forgotten and data privacy. Despite a burgeoning body of research on federated unlearning's technical feasibility, there is a paucity of literature investigating the considerations behind users' requests for data revocation. This paper proposes a non-cooperative game framework to study users' data revocation strategies in federated unlearning. We prove the existence of a Nash equilibrium. However, users' best response strategies are coupled via model performance and unlearning costs, which makes the equilibrium computation challenging. We obtain the Nash equilibrium by establishing its equivalence with a much simpler auxiliary optimization problem. We also summarize users' multi-dimensional attributes into a single-dimensional metric and derive the closed-form characterization of an equilibrium, when users' unlearning costs are negligible. Moreover, we compare the cases of allowing and forbidding partial data revocation in federated unlearning. Interestingly, the results reveal that allowing partial revocation does not necessarily increase users' data contributions or payoffs due to the game structure. Additionally, we demonstrate that positive externalities may exist between users' data revocation decisions when users incur unlearning costs, while this is not the case when their unlearning costs are negligible.

Original languageEnglish (US)
Title of host publicationIEEE INFOCOM 2024 - IEEE Conference on Computer Communications
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1151-1160
Number of pages10
ISBN (Electronic)9798350383508
DOIs
StatePublished - 2024
Event2024 IEEE Conference on Computer Communications, INFOCOM 2024 - Vancouver, Canada
Duration: May 20 2024May 23 2024

Publication series

NameProceedings - IEEE INFOCOM
ISSN (Print)0743-166X

Conference

Conference2024 IEEE Conference on Computer Communications, INFOCOM 2024
Country/TerritoryCanada
CityVancouver
Period5/20/245/23/24

Funding

This work is supported by NSF ECCS-2030251 and NSF ECCS-2216970.

Keywords

  • allowing or forbidding partial revocation
  • data revocation strategies
  • Federated unlearning
  • game theory

ASJC Scopus subject areas

  • General Computer Science
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Strategic Data Revocation in Federated Unlearning'. Together they form a unique fingerprint.

Cite this