Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learning

TL;DR

Hi-SAFE introduces a lightweight, cryptographically secure aggregation method for sign-based federated learning, enhancing privacy and efficiency in resource-constrained environments by leveraging polynomial representations and hierarchical subgrouping.

Contribution

It develops a novel polynomial-based secure aggregation framework for sign-based FL, enabling privacy-preserving majority voting with constant complexity and low overhead.

Findings

Achieves secure aggregation with constant multiplicative depth.

Reduces communication overhead compared to existing methods.

Ensures privacy of intermediate gradient signs.

Abstract

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.