1. Classification of Communication and Collaboration Apps via Advanced Deep-Learning Approaches
- Author
-
Guarino I., Aceto G., Ciuonzo D., Montieri A., Persico V., Pescape A., Guarino, I., Aceto, G., Ciuonzo, D., Montieri, A., Persico, V., and Pescape, A.
- Subjects
COVID-19 ,deep learning ,encrypted traffic ,communication app ,collaboration app ,multimodal technique ,traffic classification - Abstract
The lockdowns and lifestyle changes during the COVID-19 pandemic have caused a measurable impact on Internet traffic in terms of volumes and application mix, with a sudden increase of usage of communication and collaboration apps. In this work, we focus on five such apps, whose traffic we collect, reliably label at fine granularity (per-activity), and analyze from the viewpoint of traffic classification. To this aim, we employ state-of-art deep learning approaches to assess to which degree the apps, their different use cases (activities), and the pairs app-activity can be told apart from each other. We investigate the early behavior of the biflows composing the traffic and the effect of tuning the dimension of the input, via a sensitivity analysis. The experimental analysis highlights the figures of the different architectures, in terms of both traffic-classification performance and complexity w.r.t. different classification tasks, and the related trade-off. The outcome of this analysis is informative for a number of network management tasks, including monitoring, planning, resource provisioning, and (security) policy enforcement.
- Published
- 2021
- Full Text
- View/download PDF