Machine Learning-Based Intrusion Detection System for the Internet of Vehicles

With the advancement in vehicular technology, security has become a significant concern. Attacks in the network can be minimised if an attack can be detected earlier. The proposed model, with the help of the Intrusion Detection Model using various distinct Machine Learning algorithms along with an ensemble model, is presented to help predict any attack in the network. The goal is to perform a comparative study of different feature selection techniques and machine learning models. After that, the model that gives better accuracy in classifying or detecting various types of network attacks will be chosen as the final model. The ML algorithms selected are based on Decision Tree, Naive Bayes, K-Nearest Neighbors, Logistic Regression, Random Forest and Support Vector Machine. A comparative analysis between all these six algorithms is also performed. In order to achieve the goal, the NSL-KDD dataset was downloaded from the Kaggle repository. The proposed model was compared with existing models and found to be more effective than the existing models in terms of accuracy.