Communication-Efficient Search under Fully Homomorphic Encryption for Federated Machine Learning

TL;DR

This paper presents a novel, communication-efficient method for searching encrypted models in federated learning using fully homomorphic encryption, enabling secure and scalable data management.

Contribution

It introduces a new logarithmic-interaction search algorithm leveraging CKKS encryption's properties, enhancing privacy-preserving model management in federated learning.

Findings

Reduces network interactions logarithmically during search

Utilizes CKKS's additive and multiplicative properties effectively

Broadens federated learning applications with secure search capabilities

Abstract

Homomorphic encryption (HE) has found extensive utilization in federated learning (FL) systems, capitalizing on its dual advantages: (i) ensuring the confidentiality of shared models contributed by participating entities, and (ii) enabling algebraic operations directly on ciphertexts representing encrypted models. Particularly, the approximate fully homomorphic encryption (FHE) scheme, known as CKKS, has emerged as the de facto encryption scheme, notably supporting decimal numbers. While recent research predominantly focuses on enhancing CKKS's encryption rate and evaluation speed in the context of FL, the search operation has been relatively disregarded due to the tendency of some applications to discard intermediate encrypted models. Yet, emerging studies emphasize the importance of managing and searching intermediate models for specific applications like large-scale scientific computing, necessitating robust data provenance and auditing support. To address this, our paper introduces an innovative approach that efficiently searches for a target encrypted value, incurring only a logarithmic number of network interactions. The proposed method capitalizes on CKKS's additive and multiplicative properties on encrypted models, propagating equality comparisons between values through a balanced binary tree structure to ultimately reach a single aggregate. A comprehensive analysis of the proposed algorithm underscores its potential to significantly broaden FL's applicability and impact.