Abstract-Network security situation awareness provides the
unique high level security view based upon the security alert
events. But the complexities and diversities of security alert
data on modern networks make such analysis extremely
difficult. In this paper, we analyze the existing problems of
network security situation awareness system and propose a
framework for network security situation awareness based on
knowledge discovery. The framework consists of the modeling
of network security situation and the generation of network
security situation. The purpose of modeling is to construct the
formal model of network security situation measurement based
upon the D-S evidence theory, and support the general process
of fusing and analyzing security alert events collected from
security situation sensors. The generation of network security
situation is to extract the frequent patterns and sequential
patterns from the dataset of network security situation based
upon knowledge discovery method and transform these
patterns to the correlation rules of network security situation,
and finally to automatically generate the network security
situation graph. Application of the integrated Network
Security Situation Awareness system (Net-SSA) shows that the
proposed framework supports for the accurate modeling and
effective generation of network security situation.