MLH-IDS: A Multi-Level Hybrid Intrusion Detection Method

摘要: With the growth of networked computers and associated applications, intrusion detection has become essential to keeping networks secure. A number methods have been developed for protecting using conventional statistical as well data mining methods. Data misuse anomaly-based detection, usually encompass supervised, unsupervised outlier It is necessary that capabilities be updated with creation new attacks. This paper proposes a multi-level hybrid method uses combination outlierbased improving efficiency old The evaluated captured real-time flow packet dataset called Tezpur University system (TUIDS) dataset, distributed denial service benchmark knowledge discovery Cup 1999 version KDD (NSL-KDD) dataset. Experimental results are compared existing other classifiers. performance our very good.