Fraud Detection in Mobile Payments Utilizing Process Behavior Analysis

Roland Rieke (1) , Maria Zhdanova (1) , Jürgen Repp (1) , Romain Giot (2) , Chrystel Gaber (2)

1 Fraunhofer SIT - Fraunhofer Institute for Secure Information Technology [Darmstadt]
2 Orange Labs [Caen]

Generally, the fraud risk implies any intentional deception made for financial gain. In this paper, we consider this risk in the field of services which support transactions with electronic money. Specifically, we apply a predictive security analysis method and tool which observes the behavior with respect to the transactions within such a service and tries to match it with expected behavior given by a process model. We analyze deviations from the given behavior specification for anomalies that indicate possible misuse by money laundering activities. We evaluate the applicability of the proposed approach and the computational and detection performance of the predictive security analyzer. The aim is to detect money laundering patterns in synthetic process behavior composed of simulated logs based on properties captured from real world transaction events.

Domaines: Algorithme et structure de données [cs.DS]

Roland Rieke, Maria Zhdanova, Jürgen Repp, Romain Giot, Chrystel Gaber. Fraud Detection in Mobile Payments Utilizing Process Behavior Analysis. The 2nd International Workshop on Recent Advances in Security Information and Event Management (RaSIEM 2013), Sep 2013, France. pp.8. ⟨hal-00841002⟩