Aim: The goal of Vehicular Intrusion is to detect the attackers among Connected vehicles having unique characterstics and high mobility. The Controller Area Network (CAN Bus) is a bus communication protocol that establishes a standard for the simultaneous transmission of data between in-vehicle components. The Machine Learning algorithms are Wide-Resnet Convolutional Neural Network (CNN) and Support Vector Machine (SVM) are the two algorithms (SVM). Materials and Methods: The data was obtained from the website www.kaggle.com. Sample size of Convolutional Neural Neural Network is (N=20) and the Sample size of Support Vector Machine is (N=20) are the two classes. The increased CAN(Bus) accuracy is 85%, and the Wide-Resnet Convolutional Neural Networks accuracy is 88%. The two algorithms are used to determine the CAN Bus Intrusion's enhanced categorization or complexity. In addition, the independent sibling had a satisfied value (p<0.05) i.e α=0.01with the confidence level of 95%. Conclusion: Recognizing In-Vehicle Network Intrusion significantly seems to be better in Wide-Resnet Convolutional Neural Network (CNN) than Support Vector Machine.