论文信息 - Improvements on Self-Organizing Feature Maps for User-to-Root and Remote-to-Local Network Intrusion Detection on the 1999 KDD Cup Dataset

Improvements on Self-Organizing Feature Maps for User-to-Root and Remote-to-Local Network Intrusion Detection on the 1999 KDD Cup Dataset

The problem of network intrusion detection is one that is ever-changing, ever-evolving, and is always in need of improvement. Since the method of attack is constantly changing, intrusion detection systems must also be constantly improved in order to compensate for the threat of new attacks. This paper is written to outline the improvements made upon the original paper published by Wilson et al. in which a self-organizing feature map-based intrusion detection system was trained using the 1999 KDD Cup competition training dataset and was used to successfully classify 63% of all user-to-root attacks within the 1999 KDD Cup competition testing dataset. This result shows an improvement of over five times the number of successfully detected userto-root attacks by the winner of the 1999 KDD Cup competition, submitted by Bernard Pfahringer.

Charlie Obimbo | Ryan Wilson

[1] Christopher N. K. Mooers,et al. Performance evaluation of the self‐organizing map for feature extraction , 2006 .

[2] Ali A. Ghorbani,et al. Network Intrusion Detection and Prevention - Concepts and Techniques , 2010, Advances in Information Security.

[3] Teuvo Kohonen,et al. Self-Organization and Associative Memory, Third Edition , 1989, Springer Series in Information Sciences.

[4] Bernhard Pfahringer,et al. Winning the KDD99 classification cup: bagged boosting , 2000, SKDD.

[5] Malcolm I. Heywood,et al. Selecting Features for Intrusion Detection: A Feature Relevance Analysis on KDD 99 , 2005, PST.

[6] Zubair A. Baig,et al. An AODE-based intrusion detection system for computer networks , 2011, 2011 World Congress on Internet Security (WorldCIS-2011).