Abstract: As the Internet services spread all over the world, many kinds and a large number of security threats are increasing. Therefore, intrusion detection systems, which can effectively detect intrusion accesses, have attracted attention. This paper proposes a novel approach for feature selection based on Genetic Quantum Particle Swarm Optimization (GQPSO) attribute reduction in network intrusion detection which aiming to problem of classification algorithm with low detection speed and low detection rate in high dimensional network data intrusion detection. In the approach, selection and variation of genetic algorithm with QPSO algorithm are combined to form GQPSO algorithm; normalized mutual information between attributes defined as GQPSO algorithm fitness function to guide it’s reduction of attributes to realize optimal selection of network data feature subset. KDD99 data-set are used to experiment. The experimental result shows that the approach is more effective than QPSO and PSO algorithms in discarding independent and redundancy attributes. As a result, intrusion detection rate and speed of classification algorithm are greatly heightened by using the method.

Keywords: Genetic Quantum Particle Swarm Optimization(GOPSO); Normalized Mutual Information; Attribute reduction; Intrusion Detection; Feature Selection.