Multi-Layer Anomaly Detection in Complex Dynamic Critical Systems

Revealing anomalies to support error detection in complex systems is a promising approach when traditional detection mechanisms (i.e., based on event logs, probes and heartbeats) are considered inadequate or not applicable: anomalies in data usually suggest significant, and also critical, actionable information in a wide variety of application domains. The detection capability of such complex system can be enhanced observing different layers and indicators to achieve richer information that describe the system status. The paper describes the context and the state of the art in association with the current research direction of the author with the aim to highlight the challenges and the future works that the student aims to perform in the next years. Keywords—anomaly detection, error detection, monitoring, fault injection, SOA, Secure!