GTBNN: game-theoretic and bayesian neural networks to tackle security attacks in intelligent transportation systems

The extensive implementation of cloud computing has brought about a significant transformation in multiple industries, encompassing major corporations, individual consumers, and nascent technological advancements. Cloud computing services have been widely adopted by Intelligent Transportation Systems (ITS) in order to optimize communication, data storage, and processing capabilities. ITS infrastructure is very vulnerable to security concerns due to its sensitive nature, hence requiring the implementation of efficient Intrusion Detection Systems (IDS) to identify potential threats. This study presents a new method to improve the accuracy of IDS in identifying attacks in the ITS Cloud environment by using game theoretic and bayesian optimized bayesian neural network (GTBNN). The Game-theoretic Model effectively tackles the issue of non-cooperative behavior between attackers and defenders. This model is combined with a Bayesian Optimized Bayesian Neural Network (BNN) to achieve efficient optimization and testing. The performance of our framework is evaluated on three benchmark datasets, namely UNSW-NB15, CICIDS, and Bot-IoT. The experimental findings demonstrate significant enhancements in detection rates across all datasets, exhibiting respective increases of 9.66%, 3.75%, and 4.16% and significant decreases in False Positive Rates (FPR) of 0.01%, 0.026%, and 0.138% for the respective datasets. The presented approach utilizes game-theoretic ideas and Bayesian optimization techniques to provide a distinctive and influential solution for improving the accuracy and efficiency of IDS in protecting vital ITS infrastructure.