Evaluation of classification algorithms for intrusion detection in MANETs
Artikel i vetenskaplig tidskrift, 2012

Mobile Ad hoc Networks (MANETs) are wireless networks without fixed infrastructure based on the cooperation of independent mobile nodes. The proliferation of these networks and their use in critical scenarios (like battlefield communications or vehicular networks) require new security mechanisms and policies to guarantee the integrity, confidentiality and availability of the data transmitted. Intrusion Detection Systems used in wired networks are inappropriate in this kind of networks since different vulnerabilities may appear due to resource constraints of the participating nodes and the nature of the communication. This article presents a comparison of the effectiveness of six different classifiers to detect malicious activities in MANETs. Results show that Genetic Programming and Support Vector Machines may help considerably in detecting malicious activities in MANETs. © 2012 Elsevier B.V. All rights reserved.

Support Vector Machines

Intrusion detection

Genetic Programming


Classification algorithms


S. Pastrana

Universidad Carlos III de Madrid

Aikaterini Mitrokotsa

Ecole Polytechnique Federale de Lausanne (EPFL)

A. Orfila

Universidad Carlos III de Madrid

P. Peris-Lopez

Universidad Carlos III de Madrid

Knowledge-Based Systems

0950-7051 (ISSN)

Vol. 36 217-225


Informations- och kommunikationsteknik




Datavetenskap (datalogi)




Mer information

Senast uppdaterat