Universidad de Burgos Repositorio Repositorio
Por favor, use este identificador para citar o enlazar este ítem: http://hdl.handle.net/10259/3860

Ver estadísticas de uso
Título : Mutating network scans for the assessment of supervised classifier ensembles
Autor : Sedano, Javier
Gonzalez, Silvia
Herrero, Alvaro
Baruque, Bruno
Corchado, Emilio
Publicado en: Logic Journal of the IGPL. 2012, V. 21, n. 4, p. 630-647
Editorial : Oxford University Press
Fecha de publicación : sep-2012
ISSN : 1367-0751
DOI: 10.1093/jigpal/jzs037
Resumen : As it is well known, some Intrusion Detection Systems (IDSs) suffer from high rates of false positives and negatives. A mutation technique is proposed in this study to test and evaluate the performance of a full range of classifier ensembles for Network Intrusion Detection when trying to recognize new attacks. The novel technique applies mutant operators that randomly modify the features of the captured network packets to generate situations that could not otherwise be provided to IDSs while learning. A comprehensive comparison of supervised classifiers and their ensembles is performed to assess their generalization capability. It is based on the idea of confronting brand new network attacks obtained by means of the mutation technique. Finally, an example application of the proposed testing model is specially applied to the identification of network scans and related mutations
Palabras clave: Network intrusion detection
IDS performance
classifier ensembles
machine learning
zero-day attacks
mutation
URI : http://hdl.handle.net/10259/3860
Versión del editor: http://jigpal.oxfordjournals.org/content/early/2012/09/03/jigpal.jzs037
Aparece en las colecciones: Artículos GICAP

Ficheros en este ítem:

Fichero Descripción Tamaño Formato
Sedano-LJI_2012.pdf148,66 kBAdobe PDFVisualizar/Abrir

Los ítems del Repositorio Institucional de la Universidad de Burgos están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.

 

Valid XHTML 1.0! DSpace Software Copyright © 2002-2008 MIT and Hewlett-Packard - Sobre DSpace