Network Intrusion Detection Using CNN-based Classification Method

With the rapid advancement of Artificial Intelligence (AI) in recent years, there has been a growing body of AI-related research in the field of Network Intrusion Detection Systems (NIDSs). In this paper, a network intrusion detection method based on Convolutional Neural Network (CNN) was tested using the KDD Cup 99 dataset. Along with Sigmoid-weighted Linear Unit (SiLU) as the activation function and Stochastic Gradient Descent (SGD) as the optimizer, Batch Normalization (BN) was applied to mitigate internal covariate shift. The evaluation was carried out using performance metrics for the attack classes, which yielded good results for intrusion detection and demonstrated an impressive average accuracy rate of 99.26% after ten epochs, showcasing its promising results in intrusion detection.