As network attacks have increased in number and severity over the past few\nyears, intrusion detection system (IDS) is increasingly becoming a critical\ncomponent to secure the network. Due to large volumes of security audit data as\nwell as complex and dynamic properties of intrusion behaviors, optimizing\nperformance of IDS becomes an important open problem that is receiving more and\nmore attention from the research community. The uncertainty to explore if\ncertain algorithms perform better for certain attack classes constitutes the\nmotivation for the reported herein. In this paper, we evaluate performance of a\ncomprehensive set of classifier algorithms using KDD99 dataset. Based on\nevaluation results, best algorithms for each attack category is chosen and two\nclassifier algorithm selection models are proposed. The simulation result\ncomparison indicates that noticeable performance improvement and real-time\nintrusion detection can be achieved as we apply the proposed models to detect\ndifferent kinds of network attacks.\n