Abstract: In order to solve the problems of multi-source fusion and quantitative awareness in the study of network security situation awareness, we introduced the particle swarm optimization which could search the exponent weight for different reliability data source into the D-S evidence fusion and the multi-source fusion was obtained. Based on the fusion, we studied the threaten gene acquisition method with adaptability through the discretization to normal distribution and the situation factor extraction was accomplished. According to the fusion and factor extraction, a formal network security situation awareness method was proposed which could generate service, host and network system level situation evolution curves. The simulation experiments show that the presented fusion method can increases the detection rate and decreases the false detection rate. The formal quantitative method is able to aware the dynamic changing of the threat and meets the goal that monitors the network in an effective manner.

Key words: computer application, network security situation awareness, multi-source fusion, quantitative awareness