Network Security Using Growing Hierarchical Self-Organizing Maps

This paper presents a hierarchical self-organizing neural network for intrusion detection. The proposed neural model consists of a hierarchical architecture composed of independent growing self-organizing maps (SOMs). The SOMs have shown to be successful for the analysis of high-dimensional input data as in data mining applications such as network security. An intrusion detection system (IDS) monitors the IP packets flowing over the network to capture intrusions or anomalies. One of the techniques used for anomaly detection is building statistical models using metrics derived from observation of the user's actions. The proposed growing hierarchical SOM (GHSOM) address the limitations of the SOM related to their static architecture. Experimental results are provided by applying the well-known KDD Cup 1999 benchmark data set, which contains a great variety of simulated networks attacks. Randomly selected subsets that contain both attacks and normal records from this benchmark are used for training the GHSOM. Before training, a transformation for qualitative features present in the benchmark data set is proposed in order to compute distance among qualitative values. Comparative results with other related works are also provided.

[1]  Andreas Rauber,et al.  The growing hierarchical self-organizing map: exploratory analysis of high-dimensional data , 2002, IEEE Trans. Neural Networks.

[2]  Kymie M. C. Tan,et al.  Anomaly Detection in Embedded Systems , 2002, IEEE Trans. Computers.

[3]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[4]  Andreas Rauber,et al.  Recent Advances with the Growing Hierarchical Self-Organizing Map , 2001, WSOM.

[5]  Salvatore J. Stolfo,et al.  A data mining framework for building intrusion detection models , 1999, Proceedings of the 1999 IEEE Symposium on Security and Privacy (Cat. No.99CB36344).

[6]  Kymie M. C. Tan,et al.  Determining the operational limits of an anomaly-based intrusion detector , 2003, IEEE J. Sel. Areas Commun..

[7]  Ali A. Ghorbani,et al.  Network intrusion detection using an improved competitive learning neural network , 2004, Proceedings. Second Annual Conference on Communication Networks and Services Research, 2004..

[8]  L.L. DeLooze.  Attack Characterization and Intrusion Detection using an Ensemble of Self-Organizing Maps , 2006, 2006 IEEE Information Assurance Workshop.

[9]  Emin Anarim,et al.  An intelligent intrusion detection system (IDS) for anomaly and misuse detection in computer networks , 2005, Expert Syst. Appl..

[10]  S. T. Sarasamma,et al.  Hierarchical Kohonenen net for anomaly detection in network security , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[11]  C. Douligeris,et al.  Detecting denial of service attacks using emergent self-organizing maps , 2005, Proceedings of the Fifth IEEE International Symposium on Signal Processing and Information Technology, 2005..

[12]  Xiang-Qian Ding,et al.  Research on some problems in the Kohonen SOM algorithm , 2002, Proceedings. International Conference on Machine Learning and Cybernetics.

[13]  Salvatore J. Stolfo,et al.  Real time data mining-based intrusion detection , 2001, Proceedings DARPA Information Survivability Conference and Exposition II. DISCEX'01.

[14]  Bala Srinivasan,et al.  Dynamic self-organizing maps with controlled growth for knowledge discovery , 2000, IEEE Trans. Neural Networks Learn. Syst..

[15]  Lori L. DeLooze,et al.  Attack Characterization and Intrusion Detection using an Ensemble of Self-Organizing Maps , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[16]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[17]  Salvatore J. Stolfo,et al.  Cost-based modeling for fraud and intrusion detection: results from the JAM project , 2000, Proceedings DARPA Information Survivability Conference and Exposition. DISCEX'00.

[18]  Dorothy E. Denning,et al.  An Intrusion-Detection Model , 1987, IEEE Transactions on Software Engineering.