Inductive intrusion detection in flow-based network data using One-Class Support Vector Machines

Publikation: Beitrag in Buch/Bericht/TagungsbandKonferenzbeitragBegutachtung

64 Zitate (Scopus)

Abstract

Despite extensive research effort, ordinary anomaly detection systems still suffer from serious drawbacks such as high false alarm rates due to the enormous variety of network traffic. Also, increasingly fast network speeds pose performance problems to systems which base upon deep packet inspection. In this paper, we address these problems by proposing a novel inductive network intrusion detection system. The system operates on lightweight network flows and uses One-Class Support Vector Machines for analysis. In contrast to traditional anomaly detection systems, the system is trained with malicious rather than with benign network data. The system is suited for the load of large-scale networks and is less affected by typical problems of ordinary anomaly detection systems. Evaluations brought satisfying results which indicate that the proposed approach is interesting for further research and perfectly complements traditional signature-based intrusion detection systems.

OriginalspracheEnglisch
Titel2011 4th IFIP International Conference on New Technologies, Mobility and Security, NTMS 2011 - Proceedings
Herausgeber (Verlag)IEEE
ISBN (Print)9781424487042
DOIs
PublikationsstatusVeröffentlicht - 2011
Veranstaltung4th IFIP International Conference on New Technologies, Mobility and Security, NTMS 2011 - Paris, Frankreich
Dauer: 7 Feb 201110 Feb 2011

Publikationsreihe

Name2011 4th IFIP International Conference on New Technologies, Mobility and Security, NTMS 2011 - Proceedings

Konferenz

Konferenz4th IFIP International Conference on New Technologies, Mobility and Security, NTMS 2011
Land/GebietFrankreich
OrtParis
Zeitraum07.02.201110.02.2011

Fingerprint

Untersuchen Sie die Forschungsthemen von „Inductive intrusion detection in flow-based network data using One-Class Support Vector Machines“. Zusammen bilden sie einen einzigartigen Fingerprint.

Zitieren