期刊名称：Oriental Journal of Computer Science and Technology
印刷版ISSN：0974-6471
出版年度：2009
卷号：2
期号：1
页码：69-74
出版社：Oriental Scientific Publishing Company
摘要：Recently data mining methods have gained impor tance in addressing network security issues,including network intrusion detection-a challenging task in network security. Intrusion detection systemsaim to identify attacks with a high detection rate and a low false alarm rate.Intrusion Detection System (IDS) and Intrusion Prevention Systems (IPS) in computer networksecurity are real-time software assessment by monitoring for suspicious activity at the network andsystem layer. Software scanner allows network administrator to audit the network for vulnerabilitiesand thus securing potential holes before attackers take advantage them.The network traffic datasets provided by the DARPA 1998 offline intrusion detection projectare used in our empirical investigation, which demonstrates the feasibility and promise of unsupervisedlearning methods for network intrusion detection using UML diagrams. The goal of this paper is toplace some characteristics of good IDS and examine the positioning of intrusion detection as part ofan overall layered security strategy and a review of evaluation criteria for identifying and selecting IDS
