作者: Reza Anbarestani , Behzad Akbari , Fariba Fathi
DOI: 10.1109/IRANIANCEE.2012.6292441
关键词:
摘要: Alert correlation aims to provide an abstract and high-level view of environment security state, as one can extract attack strategies from raw intrusion alerts. Most existing alert approaches depend on either expert knowledge or predefined patterns for detecting complex steps. In this paper we a Bayesian network based approach that is able discover without need knowledge. The main goal work extracting scenarios, with taking into account the sequence actions. We also try eliminate redundant relationships in detected scenario. experimental evaluation using well-known DARPA 2000 data set shows efficiency our proposed scenarios.