Information Systems, Technology and Management

Volume 285 of the series Communications in Computer and Information Science pp 152-163

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

  • Raymond Siulai WongAffiliated withComputer Science Department, San Jose State University
  • , Teng-Sheng MohAffiliated withComputer Science Department, San Jose State University
  • , Melody MohAffiliated withComputer Science Department, San Jose State University

* Final gross prices may vary according to local VAT.

Get Access


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.


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