Abstract:
The rise of IoT tech has given birth to IoV, promising a transportation revolution through seamless vehicle-infrastructure communication. However, IoV integration poses security challenges, making vehicular networks vulnerable to cyber threats. To secure these connected vehicles and prevent accidents, data breaches, and unauthorized access, we tackle IoV cybersecurity with an advanced IDS using DL. This project is crucial for safeguarding vehicles, passengers, and the transportation system, autonomously spotting anomalies and intrusions for IoV security enhancement. It also applies to general IoV safety and also has flexibility in implementation and applicability in any subsector of IoT. In that regard, it provides safer traveling and lays a foundation for an unsafe-for attacker IoV as an emerging concept for developing smart mobility.
This project utilizes Deep Learning, the latest technology in the technological frontier, to analyze and categorize IoV. While analyzing the data collected from the cars’ sensors and conceivable communication channels, the IDS educates itself regarding the normal traffic and notifies the users if it perceives anything which can be referred to as an intrusion. Thus, the training with using of real-life data is more efficient for the training of the system. Network traffic and systems performances are provided, and analyzing of the network traffic is provided by IDS that utilizes machine learning for intrusion detection. The findings of this research aid in increasing the efficiency of the Deep Learning approach in cybersecurity and aid in fulfilling the security requirements of IoV solutions in the sphere of transportation that is experiencing a growing advancement in the connectivity of systems and technologies efficiently dependent on each other.
