Norm-Profile Construction Using Splitting Neural Gas for Anomaly Detection

Gui Song Liu; Hong Qu; Zhang Yi

doi:10.4028/www.scientific.net/AMR.629.826

Paper Titles

An Energy-Efficient Unequal Clustering Algorithm in Wireless Sensor Networks
p.801

A Decision-Making Model for Distribution Center Location during Earthquake Responses
p.808

Research on Asymmetry Information and Order Behavior in Order-Driven Market
p.815

Research on Command Process Modeling Method Based on IDEF Theory
p.820

Norm-Profile Construction Using Splitting Neural Gas for Anomaly Detection
p.826

Stability Analysis and Controller Design of Networked Control Systems with Packet Dropout
p.835

Finite-Time Control of Networked Control Systems with Bounded Packet Dropout
p.840

Design One Kind of Simplified Smart Home Monitor and Controller Based on ARM-Linux System and Information Network to the Public
p.845

Research on Key Technology of Intelligent Terminal Navigation Based on Augmented Reality
p.848

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 629Norm-Profile Construction Using Splitting Neural...

Norm-Profile Construction Using Splitting Neural Gas for Anomaly Detection

Abstract:

A neural gas network is a single-layered soft competitive neural network, which has many advantages for clustering analysis comparing to Kohonen's self-organizing map, K-means etc. This paper proposes a splitting neural gas algorithm (SNG). By initializing neurons splitting and finally deleting operations, the SNG can be used to characterize a certain class pattern effectively. We utilize the SNG to construct the profile of normal activities for anomaly detection in network security. Simulations are carried out using KDD CUP intrusion detection evaluation datasets. The experimental results showed that the SNG classifier can achieve the detection rate higher than 99% with a false positive rate lower than 1.6% and outperform many other recent supervised or unsupervised approaches.

You might also be interested in these eBooks

Material Sciences and Manufacturing Technology

View Preview

Info:

Periodical:

Advanced Materials Research (Volume 629)

Pages:

826-831

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.629.826

Citation:

Cite this paper

Online since:

December 2012

Authors:

Gui Song Liu, Hong Qu, Zhang Yi

Keywords:

Anomaly Detection, Intrusion Detection, Neural Gas Network, Pattern Construction

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Ghosh A, Schwartzbard A, A study in using neural networks for anomaly and misuse detection. Proc. 8th USENIX Security Symposium; 1999, pp.141-151.

Google Scholar

[2] Patcha A, Park JM. An overview of anomaly detection techniques: existing solutions and latest technological trends. Comput Netw 2007; 51: 3448-3470.

DOI: 10.1016/j.comnet.2007.02.001

Google Scholar

[3] Chunlin Z. Jiang J. Intrusion detection using hierarchical neural networks. Pattern Recogn Lett 2005; 26: 779-791.

Google Scholar

[4] Sarasamma ST, Zhu QA. Min-Max hyperellipsoidal clustering for anomaly detection in network security. IEEE Trans. SMC-Part B 2006; 36: 87-901.

DOI: 10.1109/tsmcb.2006.870629

Google Scholar

[5] Liu G, Yi Z, Yang S. A hierarchical intrusion detection model based on the PCA neural networks. Neurocomputing 2007; 70: 561-1568.

DOI: 10.1016/j.neucom.2006.10.146

Google Scholar

[6] Shon T, Moon J. A hybrid machine learning approach to network anomaly detection. Inform Sci 2007; 177: 3799-3821.

DOI: 10.1016/j.ins.2007.03.025

Google Scholar

[7] Martinetz TM, Berkovich SG. Neural-gas network for vector quantization and its application to time series prediction, IEEE Trans. Neural Netw 1993; 4: 558-569.

DOI: 10.1109/72.238311

Google Scholar

[8] Fritzke B. A growing neural gas network learns topologies. Advances in Neural Information Processing Systems 7, MIT Press; 1995, pp.625-632.

Google Scholar

[9] KDD Data, http: /kdd. ics. uci. edu/, Reference date: Mar. (2012).

Google Scholar