Paper 2026/2839

Practical Confidential Clustering for Federated Learning using Efficient Secret-Sharing

Cédric Prigent, CNRS, INSA Lyon, Université Lyon 1, LIRIS, UMR5205
Sonia Ben Mokhtar, CNRS, INSA Lyon, Université Lyon 1, LIRIS, UMR5205
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
Creative Commons Attribution
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}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.