Flexible Threshold Multi-client Functional Encryption for Inner Product in Federated Learning

2025-10-17

AI Summary

Existing multi-client functional encryption (MCFE) schemes lack support for dynamic client departure and flexible threshold configuration, hindering their practical deployment in federated learning (FL). To address FL-specific gradient privacy requirements, this paper proposes the first MCFE scheme enabling online client revocation and dynamic threshold setting during the encryption phase—without requiring system reinitialization. Our construction leverages MCFE to realize a non-interactive inner-product computation protocol and formally defines a security model accommodating dynamic participation. A prototype implementation and empirical evaluation demonstrate that the scheme achieves both provable security and high efficiency, maintains robustness under realistic conditions such as client dropout, and significantly enhances the practicality and deployment flexibility of FL systems.

Technology Category

• Machine Learning: Privacy
• Multiagent Systems: Mechanism Design
• Game Theory and Economic Paradigms: Mechanism Design

Application Category

• Security and Privacy: Large-scale security measurements
• 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) is a distributed machine learning paradigm that enables multiple clients to collaboratively train a shared model without disclosing their local data. To address privacy issues of gradient, several privacy-preserving machine-learning schemes based on multi-client functional encryption (MCFE) have been proposed. However, existing MCFE-based schemes cannot support client dropout or flexible threshold selection, which are essential for practical FL. In this paper, we design a flexible threshold multi-client functional encryption for inner product (FTMCFE-IP) scheme, where multiple clients generate ciphertexts independently without any interaction. In the encryption phase, clients are able to choose a threshold flexibly without reinitializing the system. The decryption can be performed correctly when the number of online clients satisfies the threshold. An authorized user are allowed to compute the inner product of the vectors associated with his/her functional key and the ciphertext, respectively, but cannot learning anything else. Especially, the presented scheme supports clients drop out. Furthermore, we provide the definition and security model of our FTMCFE-IP scheme,and propose a concrete construction. The security of the designed scheme is formally proven. Finally, we implement and evaluate our FTMCFE-IP scheme.

Problem

• Supports flexible threshold selection in federated learning
• Enables secure multi-client encryption without client interaction
• Allows decryption with client dropout and privacy preservation

Innovation

• Flexible threshold selection without system reinitialization
• Supports client dropout during federated learning process
• Computes inner product while preserving data privacy