Paper Info
Title
Hierarchical Classifier Combination and Its Application in Networks Intrusion Detection
Abstract
Intrusion detection is an effective mechanism to dealing with the attacks in computer networks. Pattern recognition techniques have been used for network intrusion detection for more than a decade. Almost all of such intrusion detection systems (IDSs) use an individual classifier to distinguish normal behavior patterns from attack signatures. Moreover these systems have a high false alarm rate and high cost. In this paper, a hierarchical classifier combiner is proposed to detect network intrusions based on the fusion of multiple well-known and efficient classifiers. The KDDCUP99 dataset is used to train and test the classifiers. The overall performance in terms of the overall error rate, average cost and the false alarm rate is investigated and discussed. Also, the performance of the proposed approach is compared with the performance of the most common non- hierarchical combination approaches as well as individual classifiers.
Year
DOI
Venue
2007
10.1109/ICDMW.2007.53
ICDM Workshops
Keywords
Field
DocType
high false alarm rate,average cost,false alarm rate,overall error rate,network intrusion detection,networks intrusion detection,network intrusion,hierarchical classifier combination,overall performance,individual classifier,intrusion detection system,intrusion detection,computer networks,error rate,testing,data mining,computer network,application software,data engineering,pattern recognition
Data mining,Computer science,Anomaly-based intrusion detection system,Information engineering,Artificial intelligence,Hierarchical classifier,Application software,Classifier (linguistics),Intrusion detection system,Pattern recognition,Word error rate,Constant false alarm rate,Machine learning
Conference
ISBN
Citations 
PageRank 
0-7695-3033-8
7
0.59
References 
Authors
10
3
Name
Order
Citations
PageRank
Morteza Analoui112424.94
Behrouz Minaei Bidgoli2282.97
Mohammad Hossein Rezvani3409.06