Immune Mobile Agent and Its Application in IDS

Abstract

AbstractIn current distributed intrusion detection systems, data is collected mostly using distributed component to send for processing center. Data is analyzed in the processing center. Nevertheless, these models have the following problems: bad real time capability, bottleneck, and single point of failure. In addition, because of the low detecting speed and high false positive rate of traditional intrusion detection system and in order to overcome these shortcomings of current intrusion detection techniques, we have constructed an immune agent by combining immune system with mobile agent. A new distributed intrusion detection model based on mobile agent is proposed in this paper. Intelligent and mobile characteristics of the agent are used to make computing move to data. The system is robust and fault-tolerant. Because mobile agent only can improve the structure of system, dynamic clonal selection algorithm is adopted for reducing false positive rate. The experimental results on KDD99 data set prove that the new model has low false positive rate and high detection rate.KeywordsMobile agentImmune agentNetwork securityDistributed intrusion detection