An intrusion detection model based on data mining over data
Lixin Liu · Journal of Central South University(Science and Technology) · 2011
Aiming at the current problems of inadequacy in intrusion-detection system response speed and detecting precision of data mining techniques based on association rules of data streams,an intrusion detection system model of MMFIID-DS based on maximal frequent pattern of data streams was proposed.A variety of pruning strategies were proposed to mine the maximal frequent itemsets on trained normal data set,abnormal data set and current data streams to establish normal and abnormal behavior pattern as well as user behavior pattern of the system in order to improve response speed of the system by greatly reducing search space.Besides,misuse detection and anomaly detection techniques were combined to implement online real-time intrusion detection and improve detection precision of the system.Both theoretical and experimental results indicate that the MMFIID-DS intrusion detection system is fairly sound in performance.