Automated Classification of Network Traffic Anomalies

Abstract

Network traffic anomalies detection and characterization has been a hot topic of research for many years. Although the field is very advanced in the detection of network traffic anomalies, accurate automated classification is still a very challenging and unmet problem. This paper presents a new algorithm for automated classification of network traffic anomalies. The algorithm relies on three steps: (i) after an anomaly has been detected, identify all (or most) related packets or flow records; (ii) use these packets or flow records to derive several distinct metrics directly related to the anomaly; and (iii) classify the anomaly using these metrics in a signature-based approach. We show how this approach can act as a filter to reduce the false positive rate of detection algorithms, while providing network operators with (additional) valuable information about detected anomalies. We validate our algorithm on two different datasets: the METROSEC project database and the MAWI traffic repository.KeywordsDetection AlgorithmAnomaly DetectionAttack ResponsePacket TraceResponsible SourceThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.