Waterfall Traffic Identification: Optimizing Classification Cascades

  • Paweł Foremski
  • Christian Callegari
  • Michele Pagano
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 522)

Abstract

The Internet transports data generated by programs which cause various phenomena in IP flows. By means of machine learning techniques, we can automatically discern between flows generated by different traffic sources and gain a more informed view of the Internet.

In this paper, we optimize Waterfall, a promising architecture for cascade traffic classification. We present a new heuristic approach to optimal design of cascade classifiers. On the example of Waterfall, we show how to determine the order of modules in a cascade so that the classification speed is maximized, while keeping the number of errors and unlabeled flows at minimum. We validate our method experimentally on 4 real traffic datasets, showing significant improvements over random cascades.

Keywords

Network management Traffic classification Machinelearning Cascade classification 

References

  1. 1.
    Karagiannis, T., Papagiannaki, K., Faloutsos, M.: Blinc: multilevel traffic classification in the dark. In: ACM SIGCOMM Computer Communication Review, vol. 35, pp. 229–240. ACM (2005)Google Scholar
  2. 2.
    Finamore, A., Mellia, M., Meo, M., Rossi, D.: KISS: stochastic packet inspection classifier for UDP traffic. IEEE/ACM Trans. Netw. 18(5), 1505–1515 (2010)Google Scholar
  3. 3.
    Bermolen, P., Mellia, M., Meo, M., Rossi, D., Valenti, S.: Abacus: accurate behavioral classification of P2P-TV traffic. Comp. Netw. 55(6), 1394–1411 (2011)Google Scholar
  4. 4.
    Nguyen, T.T., Armitage, G.: A survey of techniques for internet traffic classification using machine learning. Commun. Surv. Tutor. IEEE 10(4), 56–76 (2008)Google Scholar
  5. 5.
    Callado, A., Kamienski, C., Szabó, G., Gero, B., Kelner, J., Fernandes, S., Sadok, D.: A survey on internet traffic identification. Commun. Surv. Tutor. IEEE 11(3), 37–52 (2009)Google Scholar
  6. 6.
    Dainotti, A., Pescape, A., Claffy, K.C.: Issues and future directions in traffic classification. Netw. IEEE 26(1), 35–40 (2012)Google Scholar
  7. 7.
    Foremski, P.: On different ways to classify Internet traffic: a short review of selected publications. Theor. Appl. Inf. 25(2), 119–136 (2013)Google Scholar
  8. 8.
    Dainotti, A., Pescapé, A., Sansone, C.: Early classification of network traffic through multi-classification. In: Domingo-Pascual, J., Shavitt, Y., Uhlig, S. (eds.) TMA 2011. LNCS, vol. 6613, pp. 122–135. Springer, Heidelberg (2011) CrossRefGoogle Scholar
  9. 9.
    Foremski, P., Callegari, C., Pagano, M.: Waterfall: rapid identification of IP flows using cascade classification. In: Kwiecień, A., Gaj, P., Stera, P. (eds.) CN 2014. CCIS, vol. 431, pp. 14–23. Springer, Heidelberg (2014) CrossRefGoogle Scholar
  10. 10.
    Kuncheva, L.I.: Combining Pattern Classifiers: Methods and Algorithms. Wiley (2004)Google Scholar
  11. 11.
    Alpaydin, E., Kaynak, C.: Cascading classifiers. Kybernetika 34(4), 369–374 (1998)MATHGoogle Scholar
  12. 12.
    Chellapilla, K., Shilman, M., Simard, P.: Optimally combining a cascade of classifiers. Proceed. SPIE 6067, 207–214 (2006)Google Scholar
  13. 13.
    Abdelazeem, S.: A greedy approach for building classification cascades. In: Seventh International Conference on Machine Learning and Applications, ICMLA 2008, pp. 115–120. IEEE (2008)Google Scholar
  14. 14.
    Land, A.H., Doig, A.G.: An automatic method of solving discrete programming problems. Econometrica 28(3), 497–520 (1960)CrossRefMATHMathSciNetGoogle Scholar
  15. 15.
    Foremski, P., Callegari, C., Pagano, M.: DNS-class: immediate classification of IP flows using DNS. Int. J. Netw. Manag. 24(4), 272–288 (2014)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Paweł Foremski
    • 1
  • Christian Callegari
    • 2
  • Michele Pagano
    • 2
  1. 1.The Institute of Theoretical and Applied Informatics of the Polish Academy of SciencesGliwicePoland
  2. 2.Department of Information EngineeringUniversity of PisaPisaItaly

Personalised recommendations