A Novel Model of IDS Based on Fuzzy Cluster and Immune Principle

摘要

This paper presents a novel intrusion detection model based on fuzzy cluster and immune principle. The original rival penalized competitive learning (RPCL) algorilhra is modified in order to address the problem of different variability of variables and correlation between variables, the sensitivity to initial number of clusters is also solved. Especially, we use the extended RPCL algorithm to determine the initial number of clusters in the fuzzy cluster algorithm. The genetic algorithm is used to optimize the radius deviation for the determination of characteristic function of abnormal subspace.