Paper 2026/2839
Practical Confidential Clustering for Federated Learning using Efficient Secret-Sharing
Abstract
Federated Learning (FL) often suffers from statistical heterogeneity, where diverging data distributions prevent a single global model from achieving high utility for all participants. Clustered Federated Learning (CFL) addresses this problem by grouping similar clients to train personalized sub-models, yet performing such clustering while ensuring strict confidentially with minimal communication overhead remains a significant challenge. This paper introduces CCFL, a framework for Confidential Clustering that executes clustering logic, including distance computations and centroid updates, entirely within the encrypted domain using Replicated Secret Sharing (RSS). CCFL orchestrates a unified pipeline that integrates client-side feature extraction, an anonymization server for oblivious shuffling, and Multi-Party Computation (MPC)-based clustering to ensure both input privacy and participant unlinkability. By employing a ring-based Euclidean distance optimization, CCFL significantly reduces interactive rounds, achieving up to $46.7\times$ computational speedup under realistic LAN and WAN constraints. Our one-shot clustering approach decouples heavy cryptographic computation from the training loop, allowing the system to scale seamlessly to thousands of clients with negligible edge overhead. Finally, downstream evaluations confirm that CCFL achieves a superior privacy-utility trade-off, matching or outperforming state-of-the-art personalized FL paradigms without exposing sensitive feature geometries.
Metadata
- Available format(s)
-
PDF
- Category
- Applications
- Publication info
- Preprint.
- Keywords
- Federated LearningPersonalizationConfidential ClusteringMulti-Party Computation
- Contact author(s)
-
cedric prigent @ liris cnrs fr
sonia ben-mokhtar @ liris cnrs fr - History
- 2026-11-11: approved
- 2026-11-09: received
- See all versions
- Short URL
- https://ia.cr/2026/2839
- License
-
CC BY
BibTeX
@misc{cryptoeprint:2026/2839,
author = {Cédric Prigent and Sonia Ben Mokhtar},
title = {Practical Confidential Clustering for Federated Learning using Efficient Secret-Sharing},
howpublished = {Cryptology {ePrint} Archive, Paper 2026/2839},
year = {2026},
url = {https://eprint.iacr.org/2026/2839}
}