CVFL-Pro: A Collusion-Resistant Verification Federated Learning Framework With Adaptive Communication Optimization

Abstract

Federated learning has gained significant attention for its ability to train models without directly accessing raw data. However, the malicious server may falsify the aggregation results to save computational resources. While existing verifiable federated learning methods can validate the results, they exacerbate communication bottlenecks and fail to achieve collusion-resistant verification in the absence of a trusted authority. In this paper, we propose CVFL-Pro, a collusion-resistant verification federated learning framework with adaptive communication optimization. Specifically, we utilize a mask and Shamir’s secret sharing for privacy protection, and it is robust against client dropout. We combine a lightweight MAC scheme and auxiliary nodes to achieve efficient verifiability. Furthermore, we design an adaptive communication optimization algorithm (AOTop-<inline-formula> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula>), which dynamically adjusts the compression rate <inline-formula> <tex-math notation="LaTeX">$p$ </tex-math></inline-formula> based on the gradient magnitude and the gradient variation between rounds, ensuring optimal performance with minimal cost. Finally, we instantiate CVFL-Pro and prove its correctness and security against collusion by up to <inline-formula> <tex-math notation="LaTeX">$|N|-2$ </tex-math></inline-formula> clients (where <inline-formula> <tex-math notation="LaTeX">$|N|$ </tex-math></inline-formula> is the total number of clients) and the server. Extensive evaluations on MNIST, CIFAR-10, and CIFAR-100 datasets demonstrate that CVFL-Pro reduces communication overhead by 58.07% compared to the optimal Top-<inline-formula> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula> and 95.81% compared to SecAgg. Experiments show that CVFL-Pro reduces communication overhead by up to 95.81% while maintaining accuracy. It dynamically adjusts compression and achieves efficient storage, requiring only 830.16KB compared to 1952.62KB in SecAgg.