Active Learning for Network Traffic Classification: A Technical Study

Network Traffic Classification (NTC) has become an important feature in various network management operations, e.g., Quality of Service (QoS) provisioning and security services. Machine Learning (ML) algorithms as a popular approach for NTC can promise reasonable accuracy classification deal with encrypted traffic. However, ML-based techniques suffer from the shortage labeled traffic data which is case many real-world applications. This study investigates applicability active form ML, called Active (AL), NTC. AL reduces need large number examples by actively choosing instances that should be labeled. The first provides overview its fundamental challenges along surveying literature on methods. Then, it introduces concepts AL, discusses context NTC, review this field. Further, open issues AL-based are discussed. Moreover, technical survey, some experiments conducted to show broad simulation results achieve high small amount data.