A model of evolving intrusion detection system based on data mining and immune principle

In this paper, an IDS framework based on data mining technique and immune principle is presented. Here data mining technique is used to discover frequently occurred patterns, which are equivalent to self proteins in immune system. Immune principle is explored to generate negative detectors, which does not match any self protein based on distance metric. These negative detectors are distributed into the network system to perform anomaly detection independently and concurrently. Our experiment shows that it has low false positive rate and high detection rate.