Secure Aggregation in Federated Learning using Multiparty Homomorphic Encryption

2025-03-01

AI Summary

To address the challenges of balancing decryption fault tolerance, dynamic client participation, and efficiency in secure gradient aggregation for federated learning, this paper proposes a fault-tolerant multi-party homomorphic encryption (MPHE) framework. The method integrates Shamir’s secret sharing with gradient quantization-based compression, enabling collaborative decryption by any sufficiently sized subset of clients while supporting dynamic client joining and communication-efficient transmission. We formally prove that the scheme achieves computational security under standard cryptographic assumptions, with aggregation overhead approaching that of plaintext baselines. Experimental results demonstrate that the proposed encryption-compression co-design outperforms mainstream secure multi-party computation (MPC) approaches in decryption success rate, communication cost, and computational efficiency. The framework thus offers both practical deployability and scalability for real-world federated learning systems.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Learning to Search
• Multiagent Systems: Multiagent 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

A key operation in federated learning is the aggregation of gradient vectors generated by individual client nodes. We develop a method based on multiparty homomorphic encryption (MPHE) that enables the central node to compute this aggregate, while receiving only encrypted version of each individual gradients. Towards this end, we extend classical MPHE methods so that the decryption of the aggregate vector can be successful even when only a subset of client nodes are available. This is accomplished by introducing a secret-sharing step during the setup phase of MPHE when the public encryption key is generated. We develop conditions on the parameters of the MPHE scheme that guarantee correctness of decryption and (computational) security. We explain how our method can be extended to accommodate client nodes that do not participate during the setup phase. We also propose a compression scheme for gradient vectors at each client node that can be readily combined with our MPHE scheme and perform the associated convergence analysis. We discuss the advantages of our proposed scheme with other approaches based on secure multi-party computation. Finally we discuss a practical implementation of our system, compare the performance of our system with different approaches, and demonstrate that by suitably combining compression with encryption the overhead over baseline schemes is rather small.

Problem

• Secure aggregation of gradients in federated learning
• Multiparty homomorphic encryption for encrypted gradient computation
• Decryption with partial client participation and gradient compression

Innovation

• Multiparty homomorphic encryption for secure aggregation
• Secret-sharing during MPHE setup for partial decryption
• Combining gradient compression with encryption efficiently