loading...
A Traffic Classification Algorithm for Intrusion Detection
Niagara Falls, Ontario, Canada May 21-May 23
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/AINAW.2007.6221st International Conference on Adva ...
 This Article 
 
PDF
HTML
IEEE Xplore Subscribers
 
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Tarek Abbes, ISECS, France
Adel Bouhoula, SUP'COM, Tunisia
Michael Rusinowitch, LORIA/INRIA-Lorraine, France
We propose in this paper a new intrusion detection method for supporting high speed traffic. As in firewalls and routers, we rely on packet classification to specialize the task of several Network Intrusions Detection Systems (NIDSs). We build several traffic classes regarding the network configuration and the traffic properties. Then we consider the NIDS characteristics to select for each class the suitable intrusion detection method. Our idea offers several advantages such as load balancing, fault tolerance and attack prevention.

We express our traffic classification method by means of traffic division rules. Then we adequately construct the paths of these rules to reduce the overlapping cases. We transform the rule paths in a prefix trie that we complete by failure links to finally get a Directed Acyclic Graph (DAG). We believe that our classification method is useful for other problems such as firewalling, routing and billing.

Citation:
Tarek Abbes, Adel Bouhoula, Michael Rusinowitch, "A Traffic Classification Algorithm for Intrusion Detection," ainaw, vol. 1, pp.188-193, 21st International Conference on Advanced Information Networking and Applications Workshops (AINAW'07), 2007
Usage of this product signifies your acceptance of the Terms of Use.