DocumentCode :
2861048
Title :
Research of Intrusion Detection Based on an Improved K-means Algorithm
Author :
Wang, Shenghui
Author_Institution :
Inf. Technol. Center, China Nucl. Power Technol. Res. Inst., Shenzhen, China
fYear :
2011
fDate :
16-18 Dec. 2011
Firstpage :
274
Lastpage :
276
Abstract :
Traditional machine learning methods for intrusion detection can only detect known attacks since these methods classify data based on what they have learned. New attacks are unknown and are difficult to detect because they have not learned. In this paper, we present an improved k-means clustering-based intrusion detection method, which trains on unlabeled data in order to detect new attacks. The result of experiments run on the KDD Cup 1999 data set shows the improvement in detection rate and decrease in false positive rate and the ability to detect unknown intrusions.
Keywords :
learning (artificial intelligence); pattern clustering; security of data; KDD Cup 1999 data set; attack detection; k-means clustering-based intrusion detection method; machine learning methods; unlabeled data; Clustering algorithms; Data mining; Data models; Intrusion detection; Labeling; Training; Intrusion Detection; clustering; k-means;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Innovations in Bio-inspired Computing and Applications (IBICA), 2011 Second International Conference on
Conference_Location :
Shenzhan
Print_ISBN :
978-1-4577-1219-7
Type :
conf
DOI :
10.1109/IBICA.2011.72
Filename :
6118591
Link To Document :
بازگشت