作者: Catalin Mironeanu , Mitica Craus , Cnstian Nicolae Butincu
DOI: 10.1109/ROEDUNET.2015.7311978
关键词: Intrusion detection system 、 Computer security 、 Constant false alarm rate 、 Computer science 、 Intrusion prevention system 、 Prioritization 、 Data mining 、 Decision support system 、 Association rule learning
摘要: Due to increase in traffic volume, current commercial IDSs (Intrusion Detection Systems) usually tend produce a very large number of alarms. Although these alarms are triggered by actual intrusions, they often regular user behavior, thus increasing the false alarm rate and overwhelming security administrator. Mining algorithms that identify association rules provide an in-depth analysis breaches extend functionality IDSs. In this paper we present potential solution for reducing rate. Our approach is based on prioritization alerts, rescoring mechanism data mining techniques with multiple minimum supports.