DocumentCode :
88174
Title :
Efficient Methods for Early Protocol Identification
Author :
Hullar, Bela ; Laki, Sandor ; Gyorgy, Andras
Author_Institution :
Dept. of Phys. of Complex Syst., Eotvos Lorand Univ., Budapest, Hungary
Volume :
32
Issue :
10
fYear :
2014
fDate :
Oct. 2014
Firstpage :
1907
Lastpage :
1918
Abstract :
To manage and monitor their networks in a proper way, network operators are often interested in automatic methods that enable them to identify applications generating the traffic traveling through their networks as fast (i.e., from the first few packets) as possible. State-of-the-art packet-based traffic classification methods are either based on costly inspection of the payload of several packets in each flow or on basic flow statistics without taking into account the packet content. In this paper, we consider an intermediate approach of analyzing only the first few bytes of the first (or first few) packet(s) of each flow and propose automatic, machine-learning-based methods with very low computational complexity and memory footprint. The performance of these techniques are thoroughly analyzed, showing that outstanding early classification accuracy can be achieved on traffic traces generated by a diverse set of applications (including P2P TV and file sharing) in a laboratory environment as well as on a real-world data set collected in the network of a large European ISP.
Keywords :
IP networks; computational complexity; computer network management; learning (artificial intelligence); pattern classification; protocols; telecommunication traffic; European ISP; P2P TV; automatic machine-learning-based methods; computational complexity; early protocol identification; file sharing; memory footprint; network management; network monitoring; network operators; network traffic; packet content; packet-based traffic classification methods; traffic traces; Context; Data models; Memory management; Payloads; Protocols; Vectors; Vegetation; Traffic classification; machine learning; payload statistics;
fLanguage :
English
Journal_Title :
Selected Areas in Communications, IEEE Journal on
Publisher :
ieee
ISSN :
0733-8716
Type :
jour
DOI :
10.1109/JSAC.2014.2358832
Filename :
6911965
Link To Document :
بازگشت