Secure and Privacy-Preserving Vertical Federated Learning

2026-04-15

AI Summary

This work addresses the challenge of preserving input and output privacy in vertical federated learning settings where features are partitioned across parties and labels are not shared. To this end, the authors propose an end-to-end privacy-preserving framework that innovatively decentralizes the aggregator functionality and integrates secure multi-party computation (MPC) with differential privacy (DP). The framework introduces three efficient protocols tailored to diverse deployment environments, enabling both global and global-local model co-updating while ensuring rigorous privacy guarantees. Experimental results demonstrate that the proposed approach achieves high efficiency and effectiveness, significantly reducing the communication and computational overhead typically associated with MPC without compromising privacy or utility.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Bias, Fairness & Privacy
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Security and Privacy: Privacy-enhancing technologies
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

We propose a novel end-to-end privacy-preserving framework, instantiated by three efficient protocols for different deployment scenarios, covering both input and output privacy, for the vertically split scenario in federated learning (FL), where features are split across clients and labels are not shared by all parties. We do so by distributing the role of the aggregator in FL into multiple servers and having them run secure multiparty computation (MPC) protocols to perform model and feature aggregation and apply differential privacy (DP) to the final released model. While a naive solution would have the clients delegating the entirety of training to run in MPC between the servers, our optimized solution, which supports purely global and also global-local models updates with privacy-preserving, drastically reduces the amount of computation and communication performed using multiparty computation. The experimental results also show the effectiveness of our protocols.

Problem

• Vertical Federated Learning
• Privacy-Preserving
• Secure Multiparty Computation
• Differential Privacy
• Input and Output Privacy

Innovation

• Vertical Federated Learning
• Secure Multiparty Computation
• Differential Privacy
• Privacy-Preserving Aggregation
• Efficient Protocol Design