Belt and braces: when federated learning meets differential privacy
File(s)
Accepted version
OA Location
Author(s)
Ren, Xuebin
Yang, Shusen
Zhao, Cong
McCann, Julie
Xu, Zongben
Type
Journal Article
Abstract
Federated learning (FL) has great potential for large-scale machine learning (ML) without exposing raw data. Differential privacy (DP) is the de facto standard of privacy protection with provable guarantees. Advances in ML suggest that DP would be a perfect fit for FL with comprehensive privacy preservation. Hence, extensive efforts have been devoted to achieving practically usable FL with DP, which however is still challenging. Practitioners often not only are not fully aware of its development and categorization, but also face a hard choice between privacy and utility. Therefore, it calls for a holistic review of current advances and an investigation into the challenges and opportunities for highly usable FL systems with a DP guarantee. In this article, we first introduce the primary concepts of FL and DP, and highlight the benefits of integration. We then review the current developments by categorizing different paradigms and notions. Aiming at usable FL with DP, we present the optimization principles to seek a better tradeoff between model utility and privacy loss. Finally, we discuss future challenges in the emergent areas and relevant research topics.
Date Issued
2024-12-01
Date Acceptance
2024-11-01
Citation
Communications of the ACM, 2024, 67 (12), pp.66-77
ISSN
0001-0782
Publisher
Association for Computing Machinery (ACM)
Start Page
66
End Page
77
Journal / Book Title
Communications of the ACM
Volume
67
Issue
12
Copyright Statement
Copyright © ACM. This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
License URL
Publication Status
Published
Date Publish Online
2024-11-22