Verifiable Secure Aggregation via Dual Servers with Linear Tags in Federated Learning

2026-05-21

AI Summary

This work addresses the threat of malicious servers in federated learning, which may compromise privacy via gradient inversion or manipulate aggregation results. To counter this, the authors propose a verifiable secure aggregation scheme based on a dual non-colluding server architecture. By integrating pseudorandom functions with linear labeling techniques, the scheme constructs lightweight cryptographic primitives that provide end-to-end privacy protection and mutual verifiability while maintaining communication overhead comparable to plaintext aggregation. Experimental results demonstrate significant efficiency gains: at an input dimension of 20K, user computation time is reduced to 18 ms—7× faster than OPSA—and verification time drops to 9.5 ms, representing a 2.4× speedup, thereby substantially lowering both computational and verification costs.

Abstract

Federated learning (FL) enables collaborative model training by aggregating local updates without requiring raw data sharing. However, prior studies have shown that servers can exploit gradient inversion to compromise user privacy or manipulate aggregation results, undermining the utility of the global model. To address these concerns, we propose a secure and verifiable aggregation scheme with lightweight cryptographic primitives for FL. Our method leverages pseudo-random functions (PRFs) and a non-colluding dual-server architecture to achieve secure aggregation with mutual server verification, while maintaining communication overhead comparable to plaintext aggregation and a constant verification tag size. Crucially, it preserves user privacy and achieves end-to-end secure aggregation with verification. Moreover, our scheme significantly reduces both user computation and verification overhead, making it suitable for FL with a large number of participants. For instance, with an input dimension of 20K, user computation time is reduced to 18 ms, approximately 7$\times$ faster than OPSA, while verification time decreases to 9.5 ms, approximately 2.4$\times$ faster than OPSA.

Problem

• Federated Learning
• Secure Aggregation
• Privacy Preservation
• Verifiable Computation
• Gradient Inversion Attack

Innovation

• Secure Aggregation
• Verifiable Computation
• Dual-server Architecture
• Federated Learning
• Lightweight Cryptography