paper-with-me

Papers

DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning

2026-05-13 · Haaris Mehmood, Giorgos Tatsis, Dimitrios Alexopoulos, Karthikeyan Saravanan, Jie Xu, Anastasios Drosou, Mete Ozay arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.13708

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

TAPFed: Threshold Secure Aggregation for Privacy-Preserving Federated Learning

2025-01-09 · Runhua Xu, Bo Li, Chao Li, James B. D. Joshi 외

Federated learning is a computing paradigm that enhances privacy by enabling multiple parties to collaboratively train a machine learning model without revealing personal data. However, current research indicates that tr…

Federated LearningPrivacy Preserving

FedMPQ: Secure and Communication-Efficient Federated Learning with Multi-codebook Product Quantization

2024-04-21 · Xu Yang, Jiapeng Zhang, Qifeng Zhang, Zhuo Tang

In federated learning, particularly in cross-device scenarios, secure aggregation has recently gained popularity as it effectively defends against inference attacks by malicious aggregators. However, secure aggregation o…

Federated LearningQuantization

Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrix

2021-06-10 · Maximilian Lam, Gu-Yeon Wei, David Brooks, Vijay Janapa Reddi 외

We show that aggregated model updates in federated learning may be insecure. An untrusted central server may disaggregate user updates from sums of updates across participants given repeated observations, enabling the se…

Federated Learning

Enabling DER Participation in Frequency Regulation Markets

2020-11-08 · Priyank Srivastava, Chin-Yao Chang, Jorge Cortes

Distributed energy resources (DERs) are playing an increasing role in ancillary services for the bulk grid, particularly in frequency regulation. In this paper, we propose a framework for collections of DERs, combined to…

AdRo-FL: Informed and Secure Client Selection for Federated Learning in the Presence of Adversarial Aggregator

2025-06-21 · Md. Kamrul Hossain, Walid Aljoby, Anis Elgabli, Ahmed M. Abdelmoniem 외

Federated Learning (FL) enables collaborative learning without exposing clients' data. While clients only share model updates with the aggregator, studies reveal that aggregators can infer sensitive information from thes…

Federated LearningPrivacy Preserving