An Improved Deep Belief Network IDS on IoT-Based Network for Traffic Systems

Abstract

Internet of things (IoT) services are turning out to be more domineering with the rising security considerations fading with time. All this owes to the propagating heterogeneity and budding technologies teamed up with resource-constrained IoT systems, sculpting smart systems to be more susceptible to cyber-attacks. The security challenges such as privacy, scalability, authenticity, trust, and centralization thwart the quick adaptation of the smart services; hence, effective solutions are needed to be in place. Traditional approaches of intrusion detection mechanisms have become irrelevant now, as the bad actors often use obfuscation techniques to evade detections. Moreover, these techniques collapse, while detecting zero-day attacks. Hence, there is a need to use an intelligent mechanism based on machine learning (ML) and deep learning (DL), to detect attacks. In this study, the authors have proposed an intrusion detection engine with a deep belief network (DBN) being the core. The implementation of DBN_Classifier is performed using TensorFlow 2.0 and evaluated using a sample of the TON_IOT_Weather dataset. The findings indicate that the proposed engine outperforms the other state-of-the-art techniques with an average accuracy of 86.3%.