Smart Cities and Transportation Based Vehicle-To-Vehicle Communication and Cyber Security Analysis Using Machine Learning Model in 6G Network

Increasing number of sensor-centric communication and computer equipment installed inside cars for various purposes, such as vehicle monitoring, physical wiring reduction, driving efficiency, has made in-vehicle communication an essential part of today's driving environment. However, the relevant literature on cyber security for in-vehicle communication systems does not currently offer any targeted, workable solutions for in-vehicle cyber hazards. Current solutions usually rely on protocol-specific security techniques rather than providing a comprehensive security framework for in-vehicle communication. Cyber-physical systems (CPSs) are emergent systems that use a cyber-communication infrastructure to enable efficient real-time control and collaboration (C&C) of physical components, such as actuators, sensors, control systems, and the surrounding environment. This study analyses how smart cities are transported using machine learning models in 6G networks to analyse cyber security through vehicle-to-vehicle communication. In this case, vehicle-to-vehicle communication uses 6G networks that are built on the Internet of Things. Subsequently, reinforcement quantile spatial convolutional neural networks (RQSCNN) are used to perform the cyber security analysis. Throughput, Quality of Service (QoS), latency, computational cost, data transfer rate are all considered in experimental investigation. As a result, the suggested model can be applied in high-speed, high-throughput internal communication contexts of automobiles and accurately characterise both the nature and presence or absence of attacks.