The attacks in Vehicular Ad Hoc Networks have attracted many researchers in recent years for their potential in improving road safety, traffic efficiency and infotainment services. However, VANETs run in an open and dynamic environment, so they are subject to different security threats. Therefore, it is essential to design strong Intrusion Detection Systems. Intrusion detection systems have also been obtained within various procedures to detect intrusions based on machine learning and deep learning. In this paper, we design an Intrusion Detection System and apply Machine Learning and Deep Learning techniques to automobile networks. Machine Learning and Deep Learning systems have long been the basis for IP traffic and other uses, inspiring methods while providing concise expertise. Accuracy: The highest accuracy is obtained with the logistic regression method in machine learning and deep learning approaches with the accuracy of 99.38%. Several approaches like RNNs have been demonstrated to outperform with running accuracy and detective for each intrusion type in comparison to other methods and can further be applied. Therefore, investigating machine learning and deep learning approaches in terms of intrusion detection rate, accuracy, and false positives needs further exploration.