[en] In this paper we present a novel intrusion detection architecture based on Idiotypic Network Theory (INIDS), that aims at dealing with large scale network attacks featuring variable properties, like Denial of Service (DoS). The proposed architecture performs dynamic and adaptive clustering of the network traffic for taking fast and effective countermeasures against such high-volume attacks. INIDS is evaluated on the MITpsila99 dataset and outperforms previous approaches for DoS detection applied to this set.
Disciplines :
Sciences informatiques
Identifiants :
UNILU:UL-CONFERENCE-2009-294
Auteur, co-auteur :
OSTASZEWSKI, Marek ; University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB)
BOUVRY, Pascal ; University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC)
Seredynski, Franciszek
Co-auteurs externes :
yes
Langue du document :
Anglais
Titre :
An Approach to Intrusion Detection by Means of Idiotypic Networks Paradigm
Date de publication/diffusion :
2008
Nom de la manifestation :
IEEE World Congress on Computational Intelligence, WCCI 2008, Congress on Evolutionary Computation CEC 2008, Honk-Kong, June
Date de la manifestation :
June 2008
Sur invitation :
Oui
Manifestation à portée :
International
Titre du périodique :
IEEE World Congress on Computational Intelligence, WCCI 2008, Congress on Evolutionary Computation CEC 2008, Honk-Kong, June
