Comparative Analysis of Deep Learning Models for Network Traffic Classification

DOI

10.2991/978-94-6463-300-9_11How to use a DOI?

Keywords

network traffic classification; deep learning model; neural network

Abstract

In many sectors, network traffic categorization is a crucial duty, including network security, quality of service, and traffic engineering. Deep learning models have demonstrated potential in this area. This study used a comparative analysis method to evaluate and compare how well various models performed at categorizing network traffic. Convolutional neural networks (CNNs) excel at capturing local patterns and spatial dependencies, which are prevalent in network traffic data. On the other hand, recurrent neural networks (RNNs) are better suited for tasks that require modeling sequential dependencies over time, but they may struggle to capture the spatial characteristics of network traffic effectively. While deep learning models like CNNs hold promise, their effectiveness can vary depending on the specific characteristics of the data. It is crucial to consider the nature of the task, the available data, and the strengths and weaknesses of different models when making decisions. The results revealed the superiority of the CNN model over RNN models. The CNN achieved 77.41% accuracy, while the RNN with gate recurrent unit (RNN-GRU) model reached 45.43% accuracy and the RNN with long short-term memory (RNN-LSTM) model achieved 45.94% accuracy. In terms of precision, CNN achieved a score of 76.88%, while RNN-GRU scored 20.05% and RNN-LSTM scored 27.14%. Overall, this research underscores the importance of selecting appropriate models for categorizing network traffic.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Jinsong Liu
PY  - 2023
DA  - 2023/11/27
TI  - Comparative Analysis of Deep Learning Models for Network Traffic Classification
BT  - Proceedings of the 2023 International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2023)
PB  - Atlantis Press
SP  - 101
EP  - 109
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-300-9_11
DO  - 10.2991/978-94-6463-300-9_11
ID  - Liu2023
ER  -