Efficient Deep MSC-MBiLSTM-ECA Model for Network Intrusion Detection
Yimin Liu, Xi Guo · 2023
With the continuous improvement of the level of network information technology, network security issues are receiving more and more attention. Machine learning has been widely used in the field of network security. However, traditional machine learning methods have problems such as weak generalization ability and high difficulty in feature selection in network traffic anomaly detection. Therefore, this paper proposes a deep learning model based on a multi-scale one-dimensional convolution neural network(1D-CNN) combined with multi-layer Bi-directional Long Short Term Memory(BiLSTM) and attention mechanism to detect anomalous traffic. In this paper, we use the UNSW-NB15 dataset to simulate a real network environment to validate the model. The experimental results show that the model has a relatively high accuracy rate on the UNSW-NB15 dataset, and has better performance indicators than other commonly used algorithms.