Network Traffic Classification Based On A Deep Learning Approach Using NetFlow Data

Network traffic classification is of fundamental importance to a wide range of network activities, such as security monitoring, accounting, quality of service and forecasting for long-term provisioning purposes. This task has been increasingly implemented using machine learning methods due to the inability of conventional approaches to accommodate the increasing use of encryption. However, the application of machine learning methods to network traffic classification based on sampled NetFlow data is poorly developed despite the fact that NetFlow is a widely extended monitoring solution routinely employed by network operators. This study addresses this issue by proposing a network traffic classification module using NetFlow data in conjunction with a deep neural network. The performance of the proposed classification module is demonstrated by its application to two real-world datasets, and an average classification accuracy of 95% is obtained for similar to 1.4 million test cases. Moreover, the performance of the proposed classifier is demonstrated to be superior to three other state-of-the-art classifiers. Accordingly, the proposed module represents a promising alternative for network traffic classification.

Automated summary

Network traffic classification is crucial for various network activities, and machine learning methods are increasingly used due to the rise of encryption. However, the application of machine learning methods for network traffic classification using sampled NetFlow data is underdeveloped. This study proposes a network traffic classification module that combines NetFlow data with a deep neural network, and demonstrates its superior performance compared to other classifiers using real-world datasets.