Efficient Semi-supervised Learning BitTorrent Traffic Detection with Deep Packet and Deep Flow Inspections

  • Raymond Siulai Wong
  • Teng-Sheng Moh
  • Melody Moh
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 285)

Abstract

The peer-to-peer (P2P) technology has been well developed over the Internet. BitTorrent (BT) is one of the most popular P2P sharing protocols; BT network traffic detection has become increasingly important and yet technically challenging. In this paper we propose a new detection method that is based on an intelligent combination of Deep Packet Inspection (DPI) and Deep Flow Inspection (DFI) with semi-supervised learning. Comparing with existing methods, the new method has achieved equally high accuracy with shorter classification time. We believe that this highly effective BT detection method is not only significant to the BT community, but is also very useful to other groups that need to efficiently and correctly detect single applications.

Keywords

Deep Flow Inspection Deep Packet Inspection Classification BitTorrent Traffic Detection Peer to Peer Traffic 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Chen, H., Hu, Z., Ye, Z., Liu, W.: A New Model for P2P Traffic Identification Based on DPI and DFI. In: Int. Conf. on Inf. Eng. and Computer Science, ICIECS 2009, pp. 1–3 (2009)Google Scholar
  2. 2.
    Erman, J., Mahanti, A., Arlitt, M., Cohen, I., Williamson, C.: Offline/Realtime Traffic Classification Using Semi-Supervised Learning. IFIP Performance (October 2007)Google Scholar
  3. 3.
    Klemm, A., Lindemann, C., Vernon, M.K., Waldhorst, O.P.: Characterizing the query behavior in peer-to-peer file sharing systems. In: IMC 2004: Proceedings of the 4th ACM SIGCOMM Conference on Internet Measurement, pp. 55–67. ACM Press (2004)Google Scholar
  4. 4.
    Le, T., But, J.: Bittorrent traffic classification, CAIA Technical report 091022A, October 22 (2009), http://caia.swin.edu.au/reports/091022A/CAIA-TR-091022A.pdf
  5. 5.
    Liu, B., Li, Z., Li, Z.: Measurements of BitTorrent System Based on Netfilter. In: Int. Conf. on Computational Intelligence and Security, pp. 1470–1474 (2006)Google Scholar
  6. 6.
    Liu, F., Li, Z., Yu, J.: Applications Identification Based on the Statistics Analysis of Packet Length. In: Int. Symp. Information Engineering and Electronic Commerce, IEEC 2009, pp. 160–163 (2009)Google Scholar
  7. 7.
    Wang, C., Li, T., Chen, H.: P2P Traffic Identification Based on Double Layer Characteristics. In: Int. Conf. Information Technology and Computer Science, ITCS 2009, pp. 593–596 (2009)Google Scholar
  8. 8.
    Chapelle, O., Scholkopf, B., Zien, A. (eds.): Semi-Supervised Learning. MIT Press, Cambridge (2006)Google Scholar
  9. 9.
    Tan, P.-N., Steinbach, M., Kumar, V.: Introduction to Data Mining. Pearson Addison Wesley, USA (2006)Google Scholar
  10. 10.
    Wong, R.S., Moh, T.-S., Moh, M.: Efficient Semi-supervised Learning BitTorrent Traffic Detection - An Extended Summary. In: Bononi, L., Datta, A.K., Devismes, S., Misra, A. (eds.) ICDCN 2012. LNCS, vol. 7129, pp. 540–543. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  11. 11.
    Karagiannis, T., Papagiannaki, K., Faloutsos, M.: BLINC: Multi-Level Traffic Classification in the Dark. In: Proc. ACM SIGCOMM 2005, Philadelphia, PA (August 2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Raymond Siulai Wong
    • 1
  • Teng-Sheng Moh
    • 1
  • Melody Moh
    • 1
  1. 1.Computer Science DepartmentSan Jose State UniversitySan JoseUSA

Personalised recommendations