Title: A network traffic classification and anomaly detection method based on parallel cross-convolutional neural networks

Authors: Bailin Zou; Tianhang Liu

Addresses: Institute of Information Technology, Nanjing Police University, Nanjing 210042, China; College of Computer and Information, Hohai University, Nanjing 211100, China ' Network Security Corps, Chongqing Municipal Public Security Bureau, Chongqing 400030, China

Abstract: Network traffic anomaly detection, an effective means of network defence, can detect unknown attack behaviours and provide crucial support for network situation awareness. However, existing methods face challenges such as reliance on manually designed features, decreased classification accuracy, slow processing speeds, and loss of important information in traffic. To solve these problems, inspired by the binocular vision principle, we propose a parallel cross-convolutional neural network model. The model directly extracts original network traffic payload data as input, controlling depth. Utilising two deep convolutional neural network (CNN) data transformation streams undergoing three cross-blends, more feature information is extracted, enabling the capture of deeper traffic characteristics. Experimental results on the USTC-TFC2016 dataset demonstrate our model achieves 100% accuracy with only two epochs for 20-class classification, outperforming other similar models in detection performance.

Keywords: parallel cross-convolutional neural networks; CNN; intrusion detection; deep learning; network security; traffic classification.

DOI: 10.1504/IJSN.2024.140287

International Journal of Security and Networks, 2024 Vol.19 No.2, pp.92 - 100

Received: 09 Apr 2024
Accepted: 19 Apr 2024
Published online: 01 Aug 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article