Application of Data Mining to Network Intrusion Detection: Classifier Selection Model - Computer Science > Networking and Internet ArchitectureReportar como inadecuado




Application of Data Mining to Network Intrusion Detection: Classifier Selection Model - Computer Science > Networking and Internet Architecture - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Abstract: As network attacks have increased in number and severity over the past fewyears, intrusion detection system IDS is increasingly becoming a criticalcomponent to secure the network. Due to large volumes of security audit data aswell as complex and dynamic properties of intrusion behaviors, optimizingperformance of IDS becomes an important open problem that is receiving more andmore attention from the research community. The uncertainty to explore ifcertain algorithms perform better for certain attack classes constitutes themotivation for the reported herein. In this paper, we evaluate performance of acomprehensive set of classifier algorithms using KDD99 dataset. Based onevaluation results, best algorithms for each attack category is chosen and twoclassifier algorithm selection models are proposed. The simulation resultcomparison indicates that noticeable performance improvement and real-timeintrusion detection can be achieved as we apply the proposed models to detectdifferent kinds of network attacks.



Autor: Huy Nguyen, Deokjai Choi

Fuente: https://arxiv.org/







Documentos relacionados