Network Intrusion Detection Based on Artificial Immune Clustering
Huadong Wang · Journal of Information and Computational Science · 2013
Traditional intrusion detection classification based methods could not tackle the abnormal events in a changing network environment, because those methods need lots of labeled data for training prediction. On the other hand, the clustering algorithm based methods could not get ideal prediction results. In this paper, a novel Intrusion detection algorithm based on immune clustering algorithm is proposed. This method could automatically establish clusters and calculate the outlier factor for each data item. The advantage of this method could select the top x% of items as intrusions according users’ choosing, so we could balance intrusion detection rate and the false negative rate in different application contexts. The experiment results show that this novel algorithm is effective for intrusion detection problem.