Logo des Repositoriums
 

Visualization of anomaly detection using prediction sensitivity

dc.contributor.authorLaskov, Pavel
dc.contributor.authorRieck, Konrad
dc.contributor.authorSchäfer, Christin
dc.contributor.authorMüller, Klaus-Robert
dc.contributor.editorFederrath, Hannes
dc.date.accessioned2019-10-11T09:27:55Z
dc.date.available2019-10-11T09:27:55Z
dc.date.issued2005
dc.description.abstractVisualization 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.en
dc.identifier.isbn3-88579-391-1
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/28373
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofSicherheit 2005, Sicherheit – Schutz und Zuverlässigkeit
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-62
dc.titleVisualization of anomaly detection using prediction sensitivityen
dc.typeText/Conference Paper
gi.citation.endPage208
gi.citation.publisherPlaceBonn
gi.citation.startPage197
gi.conference.date5.-8. April 2005
gi.conference.locationRegensburg
gi.conference.sessiontitleRegular Research Papers

Dateien

Originalbündel
1 - 1 von 1
Lade...
Vorschaubild
Name:
GI-Proceedings.62-20.pdf
Größe:
229.67 KB
Format:
Adobe Portable Document Format