Combining CNNs and Bi-LSTMs for Enhanced Network Intrusion Detection: A Deep Learning Approach

Network Intrusion Detection Systems have become more popular as cloud technologies have become more widely adopted. This paper presents a network intrusion detection system using Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM) models. The NSL-KDD dataset is being used in the current study for analyzing the efficiency of the model. The data is pre-processed to handle missing values and normalize the features, and a stratified K-Fold cross-validation is used for analyzing the efficiency of the model. The results show that the combination of CNNs and Bi-LSTMs can effectively detect network intrusions and outperforms traditional intrusion detection methods. This study provides a new approach to network intrusion detection and highlights the potential of deep learning models in this field. The proposed system demonstrated exceptional performance with a high accuracy of 99.308% and a low false positive rate of below 0.23%, effectively indicating its capability to detect network intrusions while generating minimal false alarms.