EncCluster: Scalable Functional Encryption in Federated Learning through Weight Clustering and Probabilistic Filters

TL;DR

EncCluster introduces a scalable, privacy-preserving federated learning method combining weight clustering and probabilistic filters, significantly reducing communication costs and encryption time while maintaining high model accuracy.

Contribution

It presents a novel integration of model compression, decentralized functional encryption, and probabilistic data encoding to enhance privacy and efficiency in federated learning.

Findings

Reduces communication costs below FedAvg levels.

Speeds up encryption by over four times compared to baselines.

Maintains high model accuracy and privacy guarantees.

Abstract

Federated Learning (FL) enables model training across decentralized devices by communicating solely local model updates to an aggregation server. Although such limited data sharing makes FL more secure than centralized approached, FL remains vulnerable to inference attacks during model update transmissions. Existing secure aggregation approaches rely on differential privacy or cryptographic schemes like Functional Encryption (FE) to safeguard individual client data. However, such strategies can reduce performance or introduce unacceptable computational and communication overheads on clients running on edge devices with limited resources. In this work, we present EncCluster, a novel method that integrates model compression through weight clustering with recent decentralized FE and privacy-enhancing data encoding using probabilistic filters to deliver strong privacy guarantees in FL without affecting model performance or adding unnecessary burdens to clients. We performed a comprehensive evaluation, spanning various datasets and architectures, to demonstrate EncCluster's scalability across encryption levels. Our findings reveal that EncCluster significantly reduces communication costs - below even conventional FedAvg - and accelerates encryption by more than four times over all baselines; at the same time, it maintains high model accuracy and enhanced privacy assurances.