基于特征分析的多分类器融合的网络入侵检测

随着网络技术日益发展,计算机必须面对来自全球网的各种入侵。因而需要有效的入侵检测系统保护计算机远离这些未经允许的或恶意的行为,将模式识别的方法应用到入侵检测系统中,解决了传统入侵检测方法的缺陷。该文提出了一种基于特征分析的多分类器融合的入侵检测方法,并使用KDD'99中的数据进行了实验,实验结果证明该方法是有效的。

Multi-Classifier Combination Based on Feature Analysis for Network Intrusion Detection

As the network spreads to each corner of the world,computers are exposed to miscellaneous intrusion from the World Wide Web.We need effective intrusion detection system to protect our computers from these unauthorized or malicious actions.As pattern recognition method used in intrusion detection system,the limitation in traditional detection methods is cancelled.In this paper a new intrusion detection approach using multi-classifier combination based on fea-ture analysis is proposed.Experiment has been done on dataset in KDD-99and the result shows that it is an effective method.