Aim: The Purpose of Vehicular Intrusion is to apply Machine Learning methods to determine which Wireless Communication Vehicles have the best accuracy. Residual Neural Network (Resnet) and Wide Residual Neural Network (WRNs) are the two algorithms. Methods and Materials: The data was obtained from the website www.kaggle.com. Residual Neural Network (N=10) and Wide Residual Neural Network (N=10) are the two classes. The increased CAN (Bus) Residual Neural Network (RNN) accuracy is 90% and the Wide-Resnet (WRNs) 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=0.01 with the confidence level of 95%. Conclusion: Recognizing In-Vehicle Network Intrusion significantly seems to be better in Residual Neural Network (RNNs) than Wide Residual Neural Network (WRNs).