Design of mnitiple-level tree classifiers for intrusion detection system
Cheng Xiang, M.Y. Chong, Hongxu Zhu · 2005
Intrusion detection system (IDS) has recently emerged as an important component for enhancing information system security. To effectively build corresponding rules and patterns of computer attack scenarios and system vulnerabilities, data mining has been widely used in constructing and maintaining IDS. Based on statistical characteristics of specific intrusion types, a novel approach of using multiple-level tree classifiers is proposed in this paper to identify intrusions. Performance of this new algorithm is compared to other popular approaches such as MADAM ID (Lee and Stolfo, 2000)