Enhancing Security in 5G Vehicular Networks Through Machine Learning-Based Attack Detection

The vehicular networks along with 5G technology is promising and has a potential to revolutionize transportation sector, making it both smarter and safer. By analyzing data from connected vehicles, ML can improve traffic flow, predict accidents, and optimize route planning. However, challenges such as accurately predicting vehicle movements, managing computational and network resources, and ensuring data security in the cloud persist. The proposed study is presenting a comprehensive approach that combines various ML techniques with a focus on edge computing and MLbased attack detection. Edge computing improves the performance , as data is being processed closer to its source, enabling real-time decision-making. Furthermore, incorporating ML-based attack detection mechanisms strengthens network security by identifying and responding to cyber threats promptly. This integrated strategy aims to refine classification algorithms used in traffic management, resulting in more accurate predictions and efficient resource use. By harnessing the advantages of both edge and cloud computing while implementing robust security measures, this study aspires to design an efficient and more secured transportation system powered by 5G technology. The ultimate goal is to develop a system that not only improves traffic flow and reduces accidents but also ensures data security and optimal resource management, paving the way for the future of smart mobility.