Title :
Multiple classifiers combination based on protocol analysis for network intrusion detection
Author :
Guojun, Sungang Zhangli
Author_Institution :
Sch. of Inf. & Eng., Beijing Univ. of Posts & Telecommun., China
fDate :
31 Aug.-4 Sept. 2004
Abstract :
As the network spreads to each corner of the world, computers are exposed to miscellaneous intrusion from the World Wide Web. We need effective intrusion detection system to protect our computers from these unauthorized or malicious actions. As pattern recognition method used in intrusion detection system, the limitation in traditional detection methods is cancelled. In this paper a new intrusion detection approach using multiclassifier combination based on protocol analysis is proposed. Experiment has been done on dataset in KDD-99 and the result shows that it is an effective method.
Keywords :
Internet; pattern classification; protocols; security of data; telecommunication security; malicious action; multiple classifiers; network intrusion detection system; pattern recognition; protocol analysis; Application software; Computer bugs; Data security; Intrusion detection; Pattern recognition; Protection; Protocols; Telecommunication traffic; Web and internet services; Web sites;
Conference_Titel :
Signal Processing, 2004. Proceedings. ICSP '04. 2004 7th International Conference on
Print_ISBN :
0-7803-8406-7
DOI :
10.1109/ICOSP.2004.1441631