Abstract: The increase in usage of messaging apps enables us to collect the encrypted internet traffic. The classification of network traffic into different types of in-app service usages can help manage bandwidth and provide quality of service. Traditional approach of classification is based on packet inspection such as parsing HTTP headers. A system named CUMMA is developed for classifying service usage of messaging Apps, modelling user behavioural pattern, network traffic characteristics and temporal dependencies. The discriminative features of traffic classification can be extracted based on packet length and time delay. The clustering Hidden Markov algorithm is used for decomposing mixed-dialogs into sub-dialog which enables analyst to identify the service usages and analyse the behaviour of end user for encrypted internet traffic. CUMMA helps the mobile analyst identify the service usage and analyse end user behaviour for encrypted internet traffic, thus improving the effectiveness and efficiency of service usage classification.
Keywords: Encrypted Internet Traffic, In-App Analytics, Service Usage Classification, Mobile Messaging App, dialog, sub-dialog.
Title: Traffic Analysis of Encrypted Messaging in Various Services and Apps
Author: Ancy Sindhya A, Maria Sheeba M
International Journal of Computer Science and Information Technology Research
ISSN 2348-1196 (print), ISSN 2348-120X (online)
Research Publish Journals
