Early Classification of Network Traffic through Multi-classification

  • Alberto Dainotti
  • Antonio Pescapé
  • Carlo Sansone
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6613)

Abstract

In this work we present and evaluate different automated combination techniques for traffic classification. We consider six intelligent combination algorithms applied to both traditional and more recent traffic classification techniques using either packet content or statistical properties of flows. Preliminary results show that, when selecting complementary classifiers, some combination algorithms allow a further improvement – in terms of classification accuracy – over already well-performing stand-alone classification techniques. Moreover, our experiments show that the positive impact of combination is particularly significant when there are early-classification constraints, that is, when the classification of a flow must be obtained in its early stage (e.g. first 1 – 4 packets) in order to perform network operations online.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    L7-filter, Application Layer Packet Classifier for Linux, http://l7-filter.sourceforge.net
  2. 2.
    Aceto, G., Dainotti, A., de Donato, W., Pescapé, A.: PortLoad: taking the best of two worlds in traffic classification. In: IEEE INFOCOM 2010 - WiP Track (March 2010)Google Scholar
  3. 3.
    Alshammari, R., Zincir-Heywood, A.N.: Machine learning based encrypted traffic classification: identifying ssh and skype. In: CISDA 2009: Proceedings of the Second IEEE International Conference on Computational Intelligence for Security and Defense Applications, pp. 289–296. IEEE Press, Piscataway (2009)Google Scholar
  4. 4.
    Auld, T., Moore, A.W., Gull, S.F.: Bayesian neural networks for internet traffic classification. IEEE Transactions on Neural Networks 18(1), 223–239 (2007)CrossRefGoogle Scholar
  5. 5.
    Bernaille, L., Teixeira, R.: Early recognition of encrypted applications. In: Uhlig, S., Papagiannaki, K., Bonaventure, O. (eds.) PAM 2007. LNCS, vol. 4427, pp. 165–175. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  6. 6.
    Bernaille, L., Teixeira, R., Akodjenou, I., Soule, A., Salamatian, K.: Traffic classification on the fly. ACM SIGCOMM CCR 36(2), 23–26 (2006)CrossRefGoogle Scholar
  7. 7.
    Bernaille, L., Teixeira, R., Salamatian, K.: Early Application Identification. In: ACM CoNEXT (December 2006)Google Scholar
  8. 8.
    Bloch, I.: Information combination operators for data fusion: a comparative review. IEEE Trans. System Man and Cybernetics, Part A 26(1), 52–76 (1996)CrossRefGoogle Scholar
  9. 9.
    Callado, A., Kelner, J., Sadok, D., Kamienski, C.A., Fernandes, S.: Better network traffic identification through the independent combination of techniques. Journal of Network and Computer Applications 33(4), 433–446 (2010)CrossRefGoogle Scholar
  10. 10.
    Callado, A., Szabó, C.K.G., Gero, B.P., Kelner, J., Fernandes, S., Sadok, D.: A Survey on Internet Traffic Identification. IEEE Communications Surveys & Tutorials 11(3) (July 2009)Google Scholar
  11. 11.
    Carela-Español, V., Barlet-Ros, P., Solé-Simó, M., Dainotti, A., de Donato, W., Pescapé, A.: K-dimensional trees for continuous traffic classification. In: Ricciato, F., Mellia, M., Biersack, E. (eds.) TMA 2010. LNCS, vol. 6003, pp. 141–154. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  12. 12.
    Corona, I., Giacinto, G., Mazzariello, C., Roli, F., Sansone, C.: Information fusion for computer security: State of the art and open issues. Information Fusion 10(4), 274–284 (2009)CrossRefGoogle Scholar
  13. 13.
    Dainotti, A., de Donato, W., Pescapé, A.: Tie: A community-oriented traffic classification platform. In: Papadopouli, M., Owezarski, P., Pras, A. (eds.) TMA 2009. LNCS, vol. 5537, pp. 64–74. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  14. 14.
    Dainotti, A., de Donato, W., Pescapè, A., Ventre, G.: Tie: A community-oriented traffic classification platform. In: Technical Report TR-DIS-102008-TIE, Dipartimento di Informatica e Sistemistica, Universitá degli Studi di Napoli Federico II (October 2008)Google Scholar
  15. 15.
    Dainotti, A., Pescapè, A., Ventre, G.: A packet-level characterization of network traffic. In: CAMAD, pp. 38–45. IEEE, Los Alamitos (2006)Google Scholar
  16. 16.
    Gómez Sena, G., Belzarena, P.: Early traffic classification using support vector machines. In: LANC 2009: Proceedings of the 5th International Latin American Networking Conference, pp. 60–66. ACM, New York (2009)Google Scholar
  17. 17.
    Gordon, J., Shortliffe, E.: The dempster-shafer theory of evidence. In: Buchanan, B.G., Shortliffe, E. (eds.) Rule-Based Expert Systems, pp. 272–292. Addison-Wesley, Reading (1984)Google Scholar
  18. 18.
    He, H., Che, C., Ma, F., Zhang, J., Luo, X.: Traffic classification using en-semble learning and co-training. In: AIC 2008: Proceedings of the 8th Conference on Applied Informatics and Communications, pp. 458–463. World Scientific and Engineering Academy and Society (WSEAS), Stevens Point (2008)Google Scholar
  19. 19.
    Huang, Y.S., Suen, C.Y.: A method of combining multiple experts for the recognition of unconstrained handwritten numerals. IEEE Trans. Pattern Analysis and Machine Intelligence 17(1), 90–94 (1995)CrossRefGoogle Scholar
  20. 20.
    Kim, H., Claffy, K., Fomenkov, M., Barman, D., Faloutsos, M., Lee, K.: Internet traffic classification demystified: myths, caveats, and the best practices. In: CoNEXT 2008: Proceedings of the 2008 ACM CoNEXT Conference, pp. 1–12. ACM, New York (2008)Google Scholar
  21. 21.
    Kittler, J., Hatef, M., Duin, R.P.W., Matas, J.: On combining classifiers. IEEE Trans. Pattern Analysis and Machine Intelligence 20(2), 226–239 (1998)CrossRefGoogle Scholar
  22. 22.
    Kuncheva, L.I.: Combining Pattern Classifiers: Methods and Algorithms. Wiley-Interscience, Hoboken (2004)CrossRefMATHGoogle Scholar
  23. 23.
    Kuncheva, L.I., Bezdek, J.C., Duin, R.P.W.: Decision templates for multiple classifier fusion: an experimental comparison. Pattern Recognition 34(2), 299–314 (2001)CrossRefMATHGoogle Scholar
  24. 24.
    Nguyen, T.T., Armitage, G.: A Survey of Techniques for Internet Traffic Classification using Machine Learning. IEEE Communications Surveys and Tutorials (2008) (to appear)Google Scholar
  25. 25.
    Park, J., Tyan, H.R., Kuo, C.C.J.: Ga-based internet traffic classification technique for qos provisioning. In: International Conference on Intelligent Information Hiding and Multimedia Signal Processing, pp. 251–254 (2006)Google Scholar
  26. 26.
    Szabo, G., Szabo, I., Orincsay, D.: Accurate traffic classification, pp. 1–8 (June 2007)Google Scholar
  27. 27.
    Wernecke, K.D.: A coupling procedure for discrimination of mixed data. Biometrics 48, 497–506 (1992)CrossRefGoogle Scholar
  28. 28.
    Williams, N., Zander, S., Armitage, G.: Evaluating machine learning algorithms for automated network application identification. Tech. Rep. 060401B, CAIA, Swinburne Univ. (April 2006)Google Scholar
  29. 29.
    Williams, N., Zander, S., Armitage, G.: A preliminary performance comparison of five machine learning algorithms for practical ip traffic flow classification. ACM SIGCOMM CCR 36(5), 7–15 (2006)CrossRefGoogle Scholar
  30. 30.
    Wright, C.V., Monrose, F., Masson, G.M.: On inferring application protocol behaviors in encrypted network traffic. Journal of Machine Learning Research 7, 2745–2769 (2006)MathSciNetMATHGoogle Scholar
  31. 31.
    Xu, L., Krzyzak, A., Suen, C.Y.: Method of combining multiple classifiers and their application to handwritten numeral recognition. IEEE Trans. Syst. Man Cybernetics 22(3), 418–435 (1992)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Alberto Dainotti
    • 1
  • Antonio Pescapé
    • 1
  • Carlo Sansone
    • 1
  1. 1.Department of Computer Engineering and SystemsUniversitá di Napoli Federico IIItaly

Personalised recommendations