A federated semi‐supervised learning approach for network traffic classification

• Published in: International journal of network management 2023-05, Vol.33 (3), p.n/a
• Main Authors: Jin, Zhiping, Liang, Zhibiao, He, Meirong, Peng, Yao, Xue, Hanxiao, Wang, Yu
• Format: Article
• Language: English
• Subjects: Classification; Communications traffic; Deep learning; Domains; federated machine learning; Machine learning; network traffic classification; Semi-supervised learning; Servers
• ISSN: 1055-7148; 1099-1190
• DOI: 10.1002/nem.2222

Summary The classification of network traffic, which involves classifying and identifying the type of network traffic, is the most fundamental step to network service improvement and modern network management. Classic machine learning and deep learning methods have widely adopted in the field of network traffic classification. However, there are two major challenges in practice. One is the user privacy concern in cross‐domain traffic data sharing for the purpose of training a global classification model, and the other is the difficulty to obtain large amount of labeled data for training. In this paper, we propose a novel approach using federated semi‐supervised learning for network traffic classification, in which the federated server and clients from different domains work together to train a global classification model. Among them, unlabeled data are used on the client side, and labeled data are used on the server side. The experimental results derived from a public dataset show that the accuracy of the proposed approach can reach 97.81%, and the accuracy gap between the federated learning approach and the centralized training method is minimal. This work presents a federated semi‐supervised learning‐based network traffic classification scheme in which unlabeled data are used on the clients and labeled data are used on the server. The scheme consists of three stages: the data preprocessing stage, the federated pretraining stage, and the central server retraining stage.