Anomaly Detection Algorithms in Logs of Process Aware Systems

Today, there is a variety of systems that support business process as a whole or partially. However, normative systems are not appropriate for some domains (e.g. health care) as a flexible support is needed to the participants. On the other hand, while it is important to support flexibility in these systems, security requirements can not be met whether these systems do not offer extra control. This paper presents and assesses two anomaly detection algorithms in logs of Process Aware Systems (PAS). The detection of an anomalous trace is based on the "noise" which a trace makes in a process model discovered by a process mining algorithm. This paper argues that these methods can support the coexistence of security and flexibility when aggregated to a PAS.