Behavioural profiling for impostor detection in mobile networks

Authors: Zincir, I., Furnell, S. and Phippen, A.

Journal: 9th European Conference on Information Warfare and Security 2010, ECIW 2010

Pages: 334-342

ISBN: 9781622765355

Abstract:

The object of this research is to propose a new approach, using behavioural profiling as the basis of an Intrusion Detection System (IDS) to detect impostors who masquerade as legitimate users in mobile networks. In behaviour-based IDS, historical user profiles are created and then compared with the real-time ones in order to detect malicious activity. If a user changes behaviour this results in alerting the system since it is highlighted as an anomalous activity that might suggest an impostor is at work. To assess this approach C4.5 machine learning algorithm is applied over Massachusetts Institute of Technology's Reality Mining Dataset and successful results are achieved.

Source: Scopus