본문 바로가기
  • Home

Flow-based P2P Traffic Identification using SVM

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2008, 13(3), pp.123-130
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science

엄남경 1 우성희 2 Lee, Sang-ho 1

1충북대학교
2충주대학교

Accredited

ABSTRACT

To avoid some protection systems such as firewall, P2P applications have recently used to apply dynamic port numbers. Reliable estimates of P2P traffic require examination of packet payload, a methodological land mine from legal, privacy, technical, logistic, and fiscal perspectives. Indeed, access to user payload is often rendered impossible by one of these factors, inhibiting trustworthy estimation of P2P growth and dynamics. Despite various methods such as port-based and signature-based techniques, it still dose not satisfy the method which uses both qualitative and quantitative aspects. In this paper, a method using SVM mechanism which discriminate the P2P traffic from non-P2P traffics using differences between P2P and other application traffics is suggested. This is a systematic methodology to identify P2P networks, and without relying on packet payload.

Citation status

* References for papers published after 2022 are currently being built.