Advancing Robustness and Privacy in Federated Learning for Secure Autonomous Vehicle Systems

The rapid development of Autonomous Vehicle Systems (AVS) is transforming transportation, enabling safer, more efficient mobility. However, ensuring the security and privacy of sensitive data generated by AVS remains a major challenge. Federated Learning (FL) has emerged as a promising solution for AVS by enabling distributed machine learning across connected vehicles without sharing raw data, thereby enhancing privacy. Despite these advantages, FL faces critical challenges in autonomous driving environments, including high communication overhead, latency, and vulnerability to adversarial attacks. To address these challenges, we propose SecureFL, a novel framework designed to enhance the robustness and privacy of FL in autonomous vehicle systems. SecureFL consists of two main modules. The first module is a novel client selection strategy that integrates various factors to ensure efficient and robust client participation. First, we design a novel mechanism that uses an ensemble of classifiers to identify and mitigate adversarial attacks that attempt to corrupt the global learning model. Then, we propose a novel clustering scheme that groups devices exhibiting similar behaviors into clusters. This approach optimizes data transmission and reduces latency, ensuring efficient communication across the AVS network. The second module is a Graph Neural Network (GNN)-based reputation system that evaluates the reliability of vehicles based on data quality, prioritizing contributions from trustworthy sources, and dynamically adjusting participation in the FL process. SecureFL’s effectiveness is validated through simulations with real-world AVS-based attacks, demonstrating SecureFL’s capability to ensure security, privacy, and communication efficiency in federated learning for autonomous vehicles.