ABSTRACT
The openness and low cost structure of Voice over IP (VoIP) services has helped Application Service Providers to attract large numbers of subscribers over the last few years. However, as evidenced by various press reports the same reasons have unfortunately also attracted attackers and malicious users. Thus, misuse of services and fraud are currently considered as one of the biggest obstacles to VoIP providers. Fraud detection has been an active area of research and development in the banking and credit card industry. In the VoIP area, there is still hardly any research or products that can assist providers in detecting anomalous behavior. Hence, providers refer to general monitoring tools and manual search methods for identifying fraud attempts. To fill this gap, we suggest a complete solution for automatic fraud detection that alarms providers when suspicious behavior is detected. These tools can be used by VoIP providers to protect their services against losses due to fraud and identify previously uncollected revenue sources.
