Abstract As Internet of Things (IoT) devices proliferate in transportation networks, the security and resilience of those networks are increasingly important. This study suggests a novel approach based on deep learning to effectively detect intrusions in IoT-equipped transport networks.The suggested method use convolutional neural networks (CNN), a type of deep learning technique, to automatically extract useful characteristics from the massive amounts of information generated by Internet of Things (IoT) devices in transportation networks. The system can precisely identify and classify intrusions in real time by training the CNN model on a large collection of legitimate and malicious traffic patterns.Extensive experiments made use of a realistic data base to demonstrate the efficacy of the proposed strategy for a network of things-driven transport. Despite having detected several types of intrusions, the system has maintained a good false positive rate.The proposed system for detecting persistent intrusions offers strong protection for the transportation networks driven by the Internet against new threats and ensures the continuous operation of the vital transportation infrastructure. The system can adapt to new attack vectors and increase network security overall thanks to deep learning and group learning approaches.
Alan : Mühendislik
Dergi Türü : Uluslararası
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|