Re_useVFL: Reuse of Parameters-Based Verifiable Federated Learning With Privacy Preservation Using Gradient Sparsification

Abstract

Federated learning (FL) exhibits promising potential in the Industrial Internet of Things (IIoT) as it allows multiple institutions to collaboratively train a global model without sharing local data. However, there are still many privacy and security concerns in FL systems. The cloud server responsible for aggregating model parameters may be malicious, and it may distribute manipulated aggregation results that could launch nefarious attacks. Additionally, industrial agents may provide incomplete parameters, negatively impacting the global model’s performance. To address these issues, we introduce Re_useVFL, an efficient privacy-preserving full-process FL verification scheme. It integrates BLS-based signature verification, adaptive gradient sparsification (AdaGS), and Multi-Key CKKS encryption (MK-CKKS). Our scheme ensures the integrity of agents-uploaded parameters, the correctness of the cloud server’s aggregation results, and the consistency verification of distributed results, thereby providing comprehensive verification across the entire FL process. It also maintains validation accuracy even with some agents dropout during computation. The AdaGS algorithm notably reduces validation overhead by optimizing parameter sparsification and reuse. Additionally, employing MK-CKKS to protect agents privacy and prevent agent and server collusion. Our experiments on three datasets confirm that Re_useVFL achieves lower validation resource overhead compared to existing methods, demonstrating its practical effectiveness.