Konferenzbeitrag
Visualization of anomaly detection using prediction sensitivity
Lade...
Volltext URI
Dokumententyp
Text/Conference Paper
Zusatzinformation
Datum
2005
Zeitschriftentitel
ISSN der Zeitschrift
Bandtitel
Verlag
Gesellschaft für Informatik e.V.
Zusammenfassung
Visualization of learning-based intrusion detection methods is a challenging problem. In this paper we propose a novel method for visualization of anomaly detection and feature selection, based on prediction sensitivity. The method allows an expert to discover informative features for separation of normal and attack instances. Experiments performed on the KDD Cup dataset show that explanations provided by prediction sensitivity reveal the nature of attacks. Application of prediction sensitivity for feature selection yields a major improvement of detection accuracy.