A Naive Bayesian Network Intrusion Detection Algorithm Based on Principal Component Analysis

Traditional Naive Bayesian classification model does not consider the feature redundancy in intrusion forensics and neglects the difference between data attributes in different intrusion actions. This paper proposed a Naive Bayesian network intrusion detection algorithm based on the principal component analysis, it calculate the characteristic value of the original network attack data, then extract the main properties through the principal component analysis. Take the main properties as the new attribute set and the corresponding principal component contribution rate as weights to improve traditional Naive Bayesian classification algorithm. The experimental results showed that the algorithm can effectively reduce the data dimension and improve the efficiency of detection.