By increasing smart objects as high-potential computing devices and 5G technology, the Internet of Things (IoT) has emerging technology to provide a data-centric infrastructure for detecting safe device-to-device communications by supporting security and privacy issues. As 5G-enabled communication technology, Vehicle-to-Vehicle (V2V) communication provides a wirelessly exchange information connection between smart vehicles, intelligent devices and cloud-edge computing environment. This connection should be established with a safe and secured run-time protection system to avoid many critical anomalies and misbehavior problems. Detecting run-time malicious transformations with data-centric misbehaving reactions is a main challenge for autonomous vehicle communications with 5G-enabled communication technology. This paper provides a hybrid Genetic Algorithm-based Ensemble Bagged Trees (GA-EBT) algorithm for a data-centric misbehavior detection approach to support the V2V communications against malicious and misbehavior transactions. For evaluation of the proposed algorithm, four real test-cases are applied for messaging injection attacks in the V2V environments with compare to the state-of-the-art machine learning algorithms. The experimental results show that the proposed hybrid approach can achieve to optimal high rate accuracy factor with 99.999, precision and recall factors with 100% and F1-Score factor with 100% to detect unexpected cyber-attacks for the V2V communications in the IoT environment.

The Internet of Things (IoT) is a new well-structured emerging technology with communication of smart devices using the 5G technology, infrastructures of roads, vehicles, smart cities, traffic systems and user applications. The IoT applications facilitate providing prompt emergency responses, and improved quality of vehicles, and road services, with cost-effective activities in the intelligent transportation systems. According to the growth of 5G technology and complex communications between smart devices and intelligent vehicles, Federated Learning is applied to support privacy and security factors in safety-critical transportation systems using innovative prediction methods in Internet of Vehicle (IoV) environments. Therefore, Federated Learning (FL) approaches can support safety, privacy and security for the sensitive personal information of users and critical aspects of vehicles in intelligent transportation systems and IoV. This comprehensive review paper delves into the innovative integration of blockchain technology with federated learning and the dynamic domain of IoV. It extensively analyzes the primary concepts, methodologies, and challenges associated with the deployment of FL in IoV. This study categorically examines three main types of federated learning approaches vertical, horizontal, and decentralized each tailored to specific IoV communication scenarios like Vehicle-to-Vehicle (V2V), Vehicle-to-Infrastructure (V2I), and Vehicle-to-Cloud (V2C). The study emphasizes various applications of FL, including cyber-attack detection, data sharing, traffic prediction, and privacy preservation based on critical Quality of Service (QoS) factors. Finally, some main challenges and new open issues are discussed and assessed for federated machine learning approaches in the IoV.