Network Intrusion Detection Technology Based Unsupervised Outlier Detection
Guangping Chen · Journal of Chinese Computer Systems · 2007
In this paper,the framework of network intrusion detection technology Based unsupervised outlier detection is discussed.In the framework,patterns of network services are built by random forests algorithm over traffic data.Intrusions are detected by determining outliers related to the built patterns.The modification is presented on the outlier detection algorithm of random forests.The experimental results over the KDD'99 dataset also is reported.The results show that the proposed approach is comparable to previously reported unsupervised anomaly detection approaches evaluated over the KDD'99 dataset.