ABSTRACT The Internet of Vehicles (IoV) collects real‐time data on traffic, environmental conditions, and vehicle behavior through vehicle interconnection and interaction with infrastructure, providing support for the of Machine Learning (ML) in intelligent decision‐making. However, centralized learning approaches suffer from issues like privacy leakage and high communication costs. Federated Learning (FL) addresses these issues by sharing local model updates, but in IoV environments, challenges such as data heterogeneity result in slow convergence, limited communication resources, and security threats like gradient leakage. To tackle these challenges, this paper proposes Adaptive Blockchain‐based Hierarchical Federated Learning with Gradient Alignment (ABHFL). ABHFL groups vehicle nodes and RSUs into a hierarchical structure to perform local training, gradient alignment, and model aggregation at different levels. The proposed Adaptive Gradient Alignment (AGA) mechanism aligns the update directions of nodes towards the global optimal direction through multiple rounds of alignment after local gradient computation, accelerating model convergence and ensuring that the gradients uploaded contribute positively to global optimization. In addition, a lightweight Proof‐of‐Gradient‐Alignment (PoGA) consensus mechanism is designed, which performs two‐stage verification of the uploaded gradients and integrates reputation scores and blockchain storage to guarantee gradient reliability and protect against attacks. Extensive experiments demonstrate that ABHFL significantly improves model convergence, communication efficiency, and security reliability, providing an effective and robust solution for FL in IoV scenarios.
Long et al. (Mon,) studied this question.