Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Joo, Hyeong-Gun, Hong, Songnam, Lee, Seunghwan, Shin, Dong-Joon
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914168708268032
author Joo, Hyeong-Gun
Hong, Songnam
Lee, Seunghwan
Shin, Dong-Joon
author_facet Joo, Hyeong-Gun
Hong, Songnam
Lee, Seunghwan
Shin, Dong-Joon
contents Federated learning (FL) faces challenges in ensuring both privacy and communication efficiency, particularly in resource-constrained environments such as Internet of Things (IoT) and edge networks. While sign-based methods, such as sign stochastic gradient descent with majority voting (SIGNSGD-MV), offer substantial bandwidth savings, they remain vulnerable to inference attacks due to exposure of gradient signs. Existing secure aggregation techniques are either incompatible with sign-based methods or incur prohibitive overhead. To address these limitations, we propose Hi-SAFE, a lightweight and cryptographically secure aggregation framework for sign-based FL. Our core contribution is the construction of efficient majority vote polynomials for SIGNSGD-MV, derived from Fermat's Little Theorem. This formulation represents the majority vote as a low-degree polynomial over a finite field, enabling secure evaluation that hides intermediate values and reveals only the final result. We further introduce a hierarchical subgrouping strategy that ensures constant multiplicative depth and bounded per-user complexity, independent of the number of users n.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18887
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learning
Joo, Hyeong-Gun
Hong, Songnam
Lee, Seunghwan
Shin, Dong-Joon
Machine Learning
Federated learning (FL) faces challenges in ensuring both privacy and communication efficiency, particularly in resource-constrained environments such as Internet of Things (IoT) and edge networks. While sign-based methods, such as sign stochastic gradient descent with majority voting (SIGNSGD-MV), offer substantial bandwidth savings, they remain vulnerable to inference attacks due to exposure of gradient signs. Existing secure aggregation techniques are either incompatible with sign-based methods or incur prohibitive overhead. To address these limitations, we propose Hi-SAFE, a lightweight and cryptographically secure aggregation framework for sign-based FL. Our core contribution is the construction of efficient majority vote polynomials for SIGNSGD-MV, derived from Fermat's Little Theorem. This formulation represents the majority vote as a low-degree polynomial over a finite field, enabling secure evaluation that hides intermediate values and reveals only the final result. We further introduce a hierarchical subgrouping strategy that ensures constant multiplicative depth and bounded per-user complexity, independent of the number of users n.
title Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learning
topic Machine Learning
url https://arxiv.org/abs/2511.18887