A Privacy-Centric Approach: Scalable and Secure Federated Learning Enabled by Hybrid Homomorphic Encryption

2025-07-20

AI Summary

To address the high communication overhead, weak data privacy guarantees, and prohibitive computational/communication costs of existing encryption schemes in federated learning, this paper proposes a hybrid homomorphic encryption (HHE)-driven privacy-preserving framework. The framework synergistically integrates homomorphic and symmetric encryption to design a lightweight cryptographic protocol, enabling partial ciphertext computations locally at clients—thereby substantially reducing server-side decryption workload and network transmission volume. Theoretical analysis and empirical evaluation demonstrate that, compared to state-of-the-art approaches, the proposed method reduces communication volume by 37%–52%, decreases encryption/decryption latency by 41%–63%, and simultaneously satisfies semantic security and model convergence guarantees. This work establishes a novel paradigm for scalable and efficient deployment of federated learning in privacy-sensitive domains such as healthcare and finance.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Learning to Search
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Security and Privacy: Applications of cryptography
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Federated Learning (FL) enables collaborative model training without sharing raw data, making it a promising approach for privacy-sensitive domains. Despite its potential, FL faces significant challenges, particularly in terms of communication overhead and data privacy. Privacy-preserving Techniques (PPTs) such as Homomorphic Encryption (HE) have been used to mitigate these concerns. However, these techniques introduce substantial computational and communication costs, limiting their practical deployment. In this work, we explore how Hybrid Homomorphic Encryption (HHE), a cryptographic protocol that combines symmetric encryption with HE, can be effectively integrated with FL to address both communication and privacy challenges, paving the way for scalable and secure decentralized learning system.

Problem

• Reducing communication overhead in Federated Learning
• Enhancing data privacy with Hybrid Homomorphic Encryption
• Balancing computational costs for scalable decentralized learning

Innovation

• Hybrid Homomorphic Encryption for FL
• Combines symmetric and homomorphic encryption
• Enhances scalability and privacy in FL