Untitled Document
   
You are from : ( )  
     
Untitled Document
Untitled Document
 

International Journal of Information Technology & Computer Science ( IJITCS )

Abstract :

Due to the rapid increase of internet users and computer networks these days, there is an increased need for effective security monitoring systems, such as Network Intrusion Detection Systems. Many researchers concentrate their efforts on this area using different type of approaches to build reliable detection system to protect computer networks from attacks. Flow-based intrusion detection systems are one of these approaches that rely on aggregated traffic metrics. Their main advantages are host independence and usability on high speed networks. In this paper, Neural Network anomaly intrusion detection system based on flow data is proposed for detecting attacks in the network traffic. The experimental results demonstrate that the designed models are promising in terms of accuracy and computational time, and low rates of false positive alarms .

Keywords :

: Intrusion Detection system, Neural Network, NetFlow, Multilayer Perceptron, Anomaly detection

References :

  1. Internet2 NetFlow: Weekly Reports.   netflow.internet2.edu/weekly, April 2008.
  2. P. Haag. Nfsen: Netflow sensor.
  3. D. Plonka. Flowscan.   www.caida.org/tools/utilities/flowscan/, April 2008.
  4. B. Claise. Cisco Systems NetFlow Services Export   Version 9. Request for Comments: 3954, October  2004. IETF. nfsen.sourceforge.net, April 2008.
  5. Cisco IOS NetFlow Configuration Guide.   www.cisco.com, April 2008.
  6. IP Flow Information Export Working Group   www.ietf.org/html.charters/ipfix-charter.html,   April 2008.
  7. J., Muna. M. and Mehrotra M., "Intrusion Detection   System : A design perspective", 2rd International   Conference On Data Management, IMT Ghaziabad,   India. 2009.
  8. M. Panda, and M. Patra, “Building an efficient   network intrusion detection model using Self   Organizing Maps", proceeding of world academy of   science, engineering and technology, Vol. 38. 2009.
  9. M. Khattab Ali, W. Venus, and M. Suleiman Al   Rababaa, "The Affect of Fuzzification on Neural   Networks Intrusion Detection System", IEEE   computer society.2009.
  10. T. Zhou and LI Yang, "The Research of Intrusion   Detection Based on Genetic Neural Network",   Proceedings of the 2008 International Conference on   Wavelet Analysis and Pattern Recognition, Hong   Kong, IEEE.2008.
  11. J. Shum and A. Heidar Malki, "Network Intrusion   Detection System Using Neural Networks", Fourth   International Conference on Natural Computation,   IEEE computer society.2008.
  12. D. Novikov, V. Roman Yampolskiy, and L. Reznik,   "Anomaly Detection Based Intrusion Detection",  IEEE computer society.2006.
  13. I. Ahmad, S. Ullah Swati and S. Mohsin, "Intrusions   Detection Mechanism by Resilient Back Propagation  (RPROP)", European Journal of Scientific Research  ISSN 1450-216X Vol.17 No.4, pp.523-531.2007.
  14. S. Mukkamala, H. Andrew Sung, and A. Abraham,  "Intrusion detection using an ensemble of intelligent  paradigms", Journal of Network and Computer  Applications 28. pp167–182.2005.
  15. S. Jimmy and A. Heidar, "Network Intrusion   Detection System using Neural Networks", IEEE  computer society.2008.
  16. M. Vallipuram and B. Robert, "An Intelligent   Intrusion Detection System based on Neural  Network", IADIS International Conference Applied   Computing.2004.
  17. Muna Mhammad T. Jawhar,” Design Network   Intrusion Detection System using hybrid Fuzzy-  Neural Network”, International Journal of Computer   Science and Security, Volume (4).2009
  18. Rodrigo Braga,” Lightweight DDoS Flooding Attack   Detection Using NOX/OpenFlow”, 35th Annual  IEEE Conference on Local Computer Networks LCN  2010, Denver, Colorado
  19.  M. Al-Subaie, "The power of sequential learning in  anomaly intrusion detection", degree master thesis,  Queen University, Canada.2006.
  20.  D. Novikov, V. Roman Yampolskiy, and L. Reznik,  "Artificial Intelligence Approaches For Intrusion Detection", IEEE computer society.2006.
  21.  S. Lília de Sá, C. Adriana Ferrari dos Santos, S.   Demisio da Silva, and A. Montes, "A Neural  Network Application for Attack Detection in   Computer Networks", Instituto Nacional de   Pesquisas Espaciais – INPE, BRAZIL.2004.
  22. James Cannady, “Artificial neural networks for  misuse detection,” Proceedings of the 1998 National  Information Systems Security Conference   (NISSC'98), Arlington, VA, 1998.
  23. J. Ryan, M. Lin, and R. Miikkulainen, “Intrusion  Detection with Neural Networks,” AI Approaches to  Fraud Detection and Risk Management: Papers from  the 1997 AAAI Workshop, Providence, RI, pp. 72-79,  1997.
  24.  Srinivas Mukkamala, “Intrusion detection using  neural networks and support vector machine,”  Proceedings of the 2002 IEEE International  Honolulu, HI, 2002
  25. Java neural network framework,  http://neuroph.sourceforge.net/
  26.  Dima Novikov, Roman V. Yampolskiy and Leon  Reznik,2006, “ Anomaly Detection Based Intrusion  Detection”,Proceedings of the Third International Conference onInformation Technology: New  Generations, IEEE.
  27.  DARPA1998  http://www.ll.mit.edu/IST/ideval/docs/1998
  28. KDDCup1999 :  http://kdd.ics.uci.edu/databases

Untitled Document
     
Untitled Document
   
  Copyright © 2013 IJITCS.  All rights reserved. IISRC® is a registered trademark of IJITCS Properties.