Evaluation of Deep Learning Models in ITS Software-Defined Intrusion Detection Systems

Intelligent Transportation Systems (ITS), mainly Autonomous Vehicles (AV's), are susceptible to security and safety problems that risk the users' lives. Sophisticated threats can damage the security of AV's communications and computational capabilities, slowing down their integration into our daily lives. Cyber-attacks are getting more complex, posing greater hurdles in identifying intrusions effectively. Failing to prevent the intrusions could tarnish the security services' reliability, including data confidentiality, authenticity, and reliability. IDS is an overall prediction paradigm for detecting malicious network traffic in the ITS. This article studies the role of machine or deep learning in Software Defined-Intrusion Detection System (SD-IDS) in ITS; discusses the mathematical analysis of existing deep learning models and evaluates their performances on the basis of the various metrics (i.e., accuracy, precision, recall, f-measure) to observe which model gives the best results for the existing state of art. The results show that improved Recurrent Neural Networks (RNN) is best suited for the detection of SD-IDS attacks in the data plane and control plane.