Multiple SOFMs Working Cooperatively In a Vote-based Ranking System For Network Intrusion Detection

Protection from hackers on networks is currently of great importance. Recent examples of victims include the recent repeated hacking of Sony PS3, which involved 24.6 million customer accounts being vulnerable, and the hacking of websites both includ-ing US and Canadian government sites. Thus there is a drear need for effective Intrusion Detection and Prevention systems. Anomaly intrusion detection is a popular method of detecting Intrusions on Computer Networks. In 2011, Wilson and Obimbo proved that the use of Self-Organized Feature Maps (SOFM) could be used to increase the performance on KDD-99 dataset. This paper introduces a vote-based ranking system for intrusion detection based on SOFM. The experimental results are promising and are an improvement in both Wilson and Obimbo's system and the Winning system of the KDD IDS Competition.