Toward supervised anomaly detection Journal Article

  


Authors: Görnitz, N.; Kloft, M.; Rieck, K.; Brefeld, U.
Article Title: Toward supervised anomaly detection
Abstract: Anomaly detection is being regarded as an unsupervised learning task as anomalies stem from adversarial or unlikely events with unknown distributions. However, the predictive performance of purely unsupervised anomaly detection often fails to match the required detection rates in many tasks and there exists a need for labeled data to guide the model generation. Our first contribution shows that classical semi-supervised approaches, originating from a supervised classifier, are inappropriate and hardly detect new and unknown anomalies. We argue that semi-supervised anomaly detection needs to ground on the unsupervised learning paradigm and devise a novel algorithm that meets this requirement. Although being intrinsically non-convex, we further show that the optimization problem has a convex equivalent under relatively mild assumptions. Additionally, we propose an active learning strategy to automatically filter candidates for labeling. In an empirical study on network intrusion detection data, we observe that the proposed learning methodology requires much less labeled data than the state-of-the-art, while achieving higher detection accuracies. © 2013 AI Access Foundation. All rights reserved.
Keywords: unsupervised learning; algorithms; active learning strategies; detection accuracy; empirical studies; network intrusion detection; optimization problems; predictive performance; supervised classifiers; unsupervised anomaly detection; intrusion detection
Journal Title: Journal of Artificial Intelligence Research
Volume: 46
ISSN: 1076-9757
Publisher: Ai Access Foundation  
Date Published: 2013-01-01
Start Page: 235
End Page: 262
Language: English
PROVIDER: scopus
DOI/URL:

http://www.scopus.com/inward/record.url?eid=2-s2.0-84875512265&partnerID=40&md5=c769127d6662a2e9cc52264c5ab6494e
Notes: --- - "Export Date: 1 May 2013" - "CODEN: JAIRF" - "Source: Scopus"