Abstract: The rules produced by the traditional genetic algorithm for intrusion detection system are too single and lead to the low detection rate.In order to get precise and complete intrusion detection rules，this paper puts forward a method based on deterministic crowding genetic algorithm.It can get the whole global optimal solutions and keep the diversity of the population.The basic steps and case simulation of this algorithm are presented.The concrete method of creating the intrusion detection rules using this algorithm is analyzed in detail using the KDDCup99 as the testing data set.The chromosome code and fitness function are proposed.The experiments show that the algorithm is efficient and can get better intrusion detection rules.