Research on Network Anomaly Traffic Detection Based on ODCAE and BiGRU
Zhongxiao Zhou, Yuyi Ou · 2023
With the increasing volume of network traffic, traditional methods for detecting abnormal traffic struggle to handle large-scale and high-dimensional data. To address this issue, this paper proposes an anomaly traffic detection model that combines an optimized deep convolutional autoencoder (ODCAE) with Bidirectional Gated Recurrent Units (BiGRU). By applying L1 regularization to the DCAE, the risk of overfitting is reduced. Additionally, changing the conventional convolutional approach to dilated convolution allows the model to extract more interfeature information without increasing its complexity. The BiGRU is utilized to capture temporal information in the traffic data. Experimental results on the UNSW-NB15 dataset demonstrate the effectiveness of the proposed model.