Abstract:Federated learning enables collaborative model training across distributed clients, yet vanilla FL exposes client updates to the central server. Secure-aggregation schemes protect privacy against an honest-but-curious server, but existing approaches often suffer from many communication rounds, heavy public-key operations, or difficulty handling client dropouts. Recent methods like One-Shot Private Aggregation (OPA) cut rounds to a single server interaction per FL iteration, yet they impose substantial cryptographic and computational overhead on both server and clients. We propose a new protocol called DisAgg that leverages a small committee of clients called Aggregators to perform the aggregation itself: each client secret-shares its update vector to Aggregators, which locally compute partial sums and return only aggregated shares for server-side reconstruction. This design eliminates local masking and expensive homomorphic encryption, reducing endpoint computation while preserving privacy against a curious server and a limited fraction of colluding clients. By leveraging optimal trade-offs between communication and computation costs, DisAgg processes 100k-dimensional update vectors from 100k 5G clients with a 4.6x speedup compared to OPA, the previous best protocol.
| Comments: | Accepted to MLSys 2026; code available at: this https URL |
| Subjects: | Cryptography and Security (cs.CR); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.13708 [cs.CR] |
| (or arXiv:2605.13708v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2605.13708 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haaris Mehmood [view email]
[v1]
Wed, 13 May 2026 15:56:12 UTC (623 KB)