Active Learning Framework For Long-term Network Traffic Classification

Recent network traffic classification methods benefit from machine learning (ML) technology. However, there are many challenges due to the use of ML, such as lack of high-quality annotated datasets, data drifts and other effects causing aging of datasets and ML models, high volumes of network traffic, etc. This paper presents the benefits of augmenting traditional workflows of ML training&deployment and adaption of the Active Learning (AL) concept on network traffic analysis. The paper proposes a novel Active Learning Framework (ALF) to address this topic. ALF provides prepared software components that can be used to deploy an AL loop and maintain an ALF instance that continuously evolves a dataset and ML model automatically. Moreover, ALF includes monitoring, datasets quality evaluation, and optimization capabilities that enhance the current state of the art in the AL domain. The resulting solution is deployable for IP flow-based analysis of high-speed (100 Gb/s) networks, where it was evaluated for more than eight months. Additional use cases were evaluated on publicly available datasets.