Robust Network Intrusion Detection Scheme Using Long-Short Term Memory Based Convolutional Neural Networks

The intrusion detection system (IDS) is a crucial part in the network administration system to detect some types of cyber attack. IDS is categorized as a classifying machine thus it is likely to engage with the machine learning schemes. Many studies have demonstrated how to apply machine learning schemes to IDS even though they cannot provide optimum results. To tackle this issue, deep learning schemes can be considered as the solution due to its achievement in several fields. Therefore, in this study, we propose a deep learning model which is constructed based on convolutional neural network (CNN) layers and using Long-Short Term Memory (LSTM) layers called CNN-LSTM to classify every single traffic network. We use NSL-KDD dataset as the benchmark thus we can compare the performance of our proposed method with other existing works. This dataset includes two testing sets which are the first one is KDDTest⁺ while the second one is KDDTest^− 21 which is more difficult to be classified. The results show that our proposed method outperforms other existing works.