Anzeige
Erschienen in:
2011 | OriginalPaper | Buchkapitel
15. Network Intrusion Detection
verfasst von : Yong Shi, Yingjie Tian, Gang Kou, Yi Peng, Jianping Li
Erschienen in: Optimization Based Data Mining: Theory and Applications
Verlag: Springer London
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
Network intrusion refers to inappropriate, incorrect, or anomalous activities aimed at compromise computer networks. The early and reliable detection of network attacks is a pressing issue of today’s network security. Classification methods are one the major tools in network intrusion detection. A successful network intrusion detection system needs to have high classification accuracies and low false alarm rates. In this chapter, we apply the kernel-based MCLP model to the network intrusion detection. The performance of this model is tested using two network datasets. The first dataset, NeWT, is collected by the STEAL lab at University of Nebraska at Omaha, The second dataset is the KDDCUP-99 data set which was provided by DARPA in 1998 for the evaluation of intrusion detection approaches.