Home // International Journal On Advances in Security, volume 8, numbers 1 and 2, 2015 // View article


Improvement of User Profiling, Call Destination Profiling and Behavior Pattern Recognition Approaches for Telephony Toll Fraud Detection

Authors:
Anton Wiens
Sandra Kübler
Torsten Wiens
Michael Massoth

Keywords: Fraud detection; telephony; CDR; behavior profiling; statistical

Abstract:
Phone fraud attacks cause a massive loss in the telecommunication sector every year. The internet raises new potentials for these attacks. Attackers can use the internet to get illegal access to telecommunication devices such as Voice over Internet Protocol (VoIP) phones and use them for fraudulent calls to expensive destinations in overseas countries. The generated financial damage affects the attacked customers and also the telecommunications companies that provide the telecommunication services. Especially, attacks on small and medium-sized enterprises can threaten their existence. This demands protection for the customers and companies by a fraud detection system with intelligent detection techniques for detection and prevention of these fraud cases. In this work, we present two statistical online user profiling approaches, as well as a call destination profiling approach and a behavior pattern recognition approach for toll fraud detection. All four approaches show good and promising results. Especially, the results of the call destination profiling, for detection of distributed attacks on a single destination, and the behavior pattern recognition, for detection of change in a user’s behavior patterns, are promising for future work.

Pages: 1 to 15

Copyright: Copyright (c) to authors, 2015. Used with permission.

Publication date: June 30, 2015

Published in: journal

ISSN: 1942-2636