Unsupervised Anomaly Detection Using HDG-Clustering Algorithm

Authors:
Cheng-Fa Tsai;Chia-Chen Yen
Affiliations:
Department of Management Information Systems, National Pingtung University of Science and Technology, Pingtung, Taiwan 91201;Department of Management Information Systems, National Pingtung University of Science and Technology, Pingtung, Taiwan 91201
Venue:
Neural Information Processing
Year:
2008

Citing 7
Cited 1

Automatic subspace clustering of high dimensional data for data mining applications

SIGMOD '98 Proceedings of the 1998 ACM SIGMOD international conference on Management of data
Identifying Important Features for Intrusion Detection Using Support Vector Machines and Neural Networks

SAINT '03 Proceedings of the 2003 Symposium on Applications and the Internet
A New Data Clustering Approach for Data Mining in Large Databases

ISPAN '02 Proceedings of the 2002 International Symposium on Parallel Architectures, Algorithms and Networks
ACODF: a novel data clustering approach for data mining in large databases

Journal of Systems and Software - Special issue: Performance modeling and analysis of computer systems and networks
Unsupervised anomaly detection in network intrusion detection using clusters

ACSC '05 Proceedings of the Twenty-eighth Australasian conference on Computer Science - Volume 38
ANGEL: a new effective and efficient hybrid clustering technique for large databases

PAKDD'07 Proceedings of the 11th Pacific-Asia conference on Advances in knowledge discovery and data mining
KIDBSCAN: a new efficient data clustering algorithm

ICAISC'06 Proceedings of the 8th international conference on Artificial Intelligence and Soft Computing

The investigation of discovering potential musical instruments teachers by effective data clustering scheme

WSEAS Transactions on Computers

Quantified Score

Hi-index	0.00

Visualization

Abstract

As intrusion posing a serious security threat in network environments, many network intrusion detection schemes have been proposed in recent years. Most such methods employ signature-based or data-mining based techniques that rely on labeled training data, but cannot detect new types of attacks. Anomaly detection techniques can be adopted to solve this problem with purely normal data. However, extracting these data is a very costly task. Unlike the approaches that rely on labeled data or purely normal data, unsupervised anomaly detection can discover "unseen" attacks by unlabeled data. This investigation presents a new mixed clustering algorithm named HDG-Clustering for unsupervised anomaly detection. The proposed algorithm is evaluated using the 1999 KDD Cup data set. Experimental results indicate that the proposed approach outperforms several existing techniques.