Statistical Pattern Recognition Based Content Analysis on Encrypted Network: Traffic for the TeamViewer Application
Authors:
- Robert AltschaffelRARobert Altschaffel
- Robert ClausingRCRobert Clausing
- Christian KraetzerCKChristian Kraetzer
- Tobias HoppeTHTobias Hoppe
- Stefan KiltzSKStefan Kiltz
- Jana DittmannJDJana Dittmann
- 1 March 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 113-121
Abstract
In the course of a forensic investigation it might be required to distinguish between different network activities. While various means to analyse network traffic exist, encrypted traffic often makes such an analysis problematic. The focus of this paper is to introduce a method based on statistical pattern recognition on network recordings of encrypted sessions to distinguish between different actions within these sessions. For demonstration purposes the popular remote support and online-meeting application TeamViewer is selected to introduce and discuss an approach to distinguish between file transfers, voice conferences, video conferences, text chat and normal remote sessions within TeamViewer sessions.Keywords
This publication has 7 references indexed in Scilit:
- Side-Channel Leaks in Web Applications: A Reality Today, a Challenge Tomorrow2010
- The WEKA data mining softwareACM SIGKDD Explorations Newsletter, 2009
- Network traffic classification based on ensemble learning and co-trainingScience China Information Sciences, 2009
- Clustering Documents with Active Learning Using Wikipedia2008
- Empirical Analysis of Application-Level Traffic Classification Using Supervised Machine Learning2008
- Accurate Classification of the Internet Traffic Based on the SVM Method2007
- The Equivalence of Weighted Kappa and the Intraclass Correlation Coefficient as Measures of ReliabilityEducational and Psychological Measurement, 1973