[Back]


Talks and Poster Presentations (with Proceedings-Entry):

P. Svoboda, E. Hyytiä, F. Ricciato, M. Rupp:
"Detection and Tracking of Skype by exploiting Cross Layer Information in a live 3G Network";
Talk: 1st International Workshop on Traffic Monitoring and Analysis (TMA'09), Aachen, TU Aachen; 05-11-2009 - 05-13-2009; in: "Traffic Monitoring and Analysis: First International Workshop, TMA 2009, Aachen, Germany, May 11, 2009, Proceedings: 5537", Springer, Berlin;, 1 / 1 / Berlin (2009), ISBN: 3642016448.



English abstract:
This paper introduces a new method to detect and track
Skype traffic and users by exploiting cross layer information available
within 3G mobile cellular networks. In a 3G core network all flows can
be analyzed on a per user basis. A detected Skype message is therefore
related to a specific user. This information enables user profiles that provide
a relationship between the mobile station and the characteristics of
the corresponding Skype instance, which remain unchanged for long periods
of time. Based on this information, our computationally lightweight
method is able to classify Skype flows accurately. Moreover, the method
is, by design, robust against false positives. Based on test traces from a
live network, our new method achieves a similar detection performance
as publicly available tools, yet with much less complexity.

German abstract:
This paper introduces a new method to detect and track
Skype traffic and users by exploiting cross layer information available
within 3G mobile cellular networks. In a 3G core network all flows can
be analyzed on a per user basis. A detected Skype message is therefore
related to a specific user. This information enables user profiles that provide
a relationship between the mobile station and the characteristics of
the corresponding Skype instance, which remain unchanged for long periods
of time. Based on this information, our computationally lightweight
method is able to classify Skype flows accurately. Moreover, the method
is, by design, robust against false positives. Based on test traces from a
live network, our new method achieves a similar detection performance
as publicly available tools, yet with much less complexity.

Keywords:
traffic, classification, skype, cellular mobile network


Electronic version of the publication:
http://publik.tuwien.ac.at/files/PubDat_184256.pdf



Related Projects:
Project Head Markus Rupp:
DARWIN+: Data Analysis and Reporting in WIreless Networks

Project Head Markus Rupp:
Mobilkom


Created from the Publication Database of the Vienna University of Technology.