Title
Multiobjective classification with moGEP: an application in the network traffic domain
Abstract
The paper proposes a multiobjective approach to the problem of malicious network traffic classification, with specificity and sensitivity criteria as objective functions for the problem. The multiobjective version of Gene Expression Programming (GEP) called moGEP is proposed and applied to find proper classifiers in the multiobjective search space. The purpose of the classifiers is to discriminate information about the network traffic obtained from Idiotypic Network-based Intrusion Detection System (INIDS), transformed into time series. The proposed approach is validated using the network traffic simulator ns2. Classifiers of high accuracy are obtained and their diversity offers interesting possibilities to the domain of network security.
Year
DOI
Venue
2009
10.1145/1569901.1569989
GECCO
Keywords
Field
DocType
malicious network traffic classification,idiotypic network-based intrusion detection,gene expression programming,multiobjective search space,network traffic simulator ns2,network traffic,network security,network traffic domain,multiobjective approach,multiobjective version,multiobjective classification,multi objective optimization,objective function,intrusion detection system,denial of service,search space,time series
Traffic classification,Gene expression programming,Data mining,Mathematical optimization,Denial-of-service attack,Computer science,Network security,Multi-objective optimization,Artificial intelligence,Intrusion detection system,Network traffic simulation,Machine learning
Conference
Citations 
PageRank 
References 
2
0.36
4
Authors
3
Name
Order
Citations
PageRank
Marek Ostaszewski1297.04
Pascal Bouvry220.36
Franciszek Seredynski336655.06