Evolving discrete-valued anomaly detectors for a network intrusion detection system using negative selection
Evolving discrete-valued anomaly detectors for a network intrusion detection system using negative selection
Network intrusion detection is the problem of detecting unauthorised use of, or access to, computer systems over a network. One approach is anomaly detection, where deviations from a model of normal network activity are reported. The negative selection algorithm, inspired by the immune system, can be used to generate anomaly detectors. Previous work has applied a genetic algorithm to generate real-valued detectors. However, we argue that at least some discrete fields are required in detectors, e.g. the port number. The system reported in this paper evolves discrete-valued detectors, which we show are able to outperform real-valued detectors.
artificial immune system, intrusion detection, negative selection
41-48
Powers, Simon T.
99f673bb-debc-4c1f-90d3-78724a6020bb
He, Jun
d190c383-8093-4c9c-aade-c3a1fb3ae78f
Wang, Xue Z.
5d5284a7-dc3f-4741-9dcb-6353f2529347
Li, Rui Fa
1853c957-b633-4c46-86ce-6258709cfa76
2006
Powers, Simon T.
99f673bb-debc-4c1f-90d3-78724a6020bb
He, Jun
d190c383-8093-4c9c-aade-c3a1fb3ae78f
Wang, Xue Z.
5d5284a7-dc3f-4741-9dcb-6353f2529347
Li, Rui Fa
1853c957-b633-4c46-86ce-6258709cfa76
Powers, Simon T. and He, Jun
(2006)
Evolving discrete-valued anomaly detectors for a network intrusion detection system using negative selection.
Wang, Xue Z. and Li, Rui Fa
(eds.)
the 6th UK Workshop on Computational Intelligence (UKCI'06), University of Leeds.
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
Network intrusion detection is the problem of detecting unauthorised use of, or access to, computer systems over a network. One approach is anomaly detection, where deviations from a model of normal network activity are reported. The negative selection algorithm, inspired by the immune system, can be used to generate anomaly detectors. Previous work has applied a genetic algorithm to generate real-valued detectors. However, we argue that at least some discrete fields are required in detectors, e.g. the port number. The system reported in this paper evolves discrete-valued detectors, which we show are able to outperform real-valued detectors.
Text
2006ukci.pdf
- Other
More information
Published date: 2006
Additional Information:
Event Dates: 04/09/2006
Venue - Dates:
the 6th UK Workshop on Computational Intelligence (UKCI'06), University of Leeds, 2006-09-04
Keywords:
artificial immune system, intrusion detection, negative selection
Organisations:
Electronics & Computer Science
Identifiers
Local EPrints ID: 264052
URI: http://eprints.soton.ac.uk/id/eprint/264052
PURE UUID: e84b3140-ff7f-47a8-a598-580162147beb
Catalogue record
Date deposited: 23 May 2007
Last modified: 14 Mar 2024 07:41
Export record
Contributors
Author:
Simon T. Powers
Author:
Jun He
Editor:
Xue Z. Wang
Editor:
Rui Fa Li
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics