DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909040567648256 |
|---|---|
| author | Mehmood, Haaris Tatsis, Giorgos Alexopoulos, Dimitrios Saravanan, Karthikeyan Xu, Jie Drosou, Anastasios Ozay, Mete |
| author_facet | Mehmood, Haaris Tatsis, Giorgos Alexopoulos, Dimitrios Saravanan, Karthikeyan Xu, Jie Drosou, Anastasios Ozay, Mete |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13708 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning Mehmood, Haaris Tatsis, Giorgos Alexopoulos, Dimitrios Saravanan, Karthikeyan Xu, Jie Drosou, Anastasios Ozay, Mete Cryptography and Security Distributed, Parallel, and Cluster Computing Machine Learning 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. |
| title | DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning |
| topic | Cryptography and Security Distributed, Parallel, and Cluster Computing Machine Learning |
| url | https://arxiv.org/abs/2605.13708 |