This paper presents the development of an Intrusion Detection System (IDS) for smart vehicles utilizing advanced machine learning algorithms. The system is designed to detect and classify various types of cyberattacks, such as Distributed Denial of Service (DDoS), Fuzzy, and Impersonation attacks, alongside normal "Free" traffic. The dataset used for model training and evaluation is the CAN-intrusion-dataset, which contains crucial vehicle communication features, including Message ID, Byte-level signals, and Target labels. The study employs a range of machine learning models, including Random Forest, Gradient Boosting, AdaBoost, LSTM, and CatBoost classifiers, to identify and mitigate potential threats. By leveraging the power of these algorithms, the system aims to provide robust and real-time detection of anomalous behaviour in vehicular networks, enhancing the security and reliability of smart vehicle systems. The ultimate goal is to develop an efficient and scalable IDS capable of protecting smart vehicles from evolving cyber threats.

Keywords: Random Forest, Gradient Boosting, AdaBoost, LSTM, and CatBoost classifiers