Aim: The main objective of the Vehicular Intrusion detection system is to improve the safety of wireless vehicular communication efficiency and waiting time on the road using the algorithms in Machine Learning. Methods and Materials: The categorizing is performed by adopting a sample size of N=20 in Convolutional Neural Neural Network (N=20) and a sample size of N=20 in Support Vector Machine algorithms. The dataset is collected from www.kaggle.com. Result: The Support vector machine recognized the intrusion in the CAN bus with 85% accuracy while for the Novel Convolution Neural Networks it was 95%. The independent significant value p=0.442 (p<0.05) showed that there is no significant difference between the two models considered. Conclusion: Recognizing In-Vehicle Network Intrusion significantly seems to be better in Novel Convolution Neural Network (CNN) than Support Vector Machine.