The paper describes about a method of intrusion detection that uses machine learning algorithms. Here we discuss about the combinational use of two machine learning algorithms called Principal Component Analysis and Naive Bayes classifier. The dimensionality of the dataset is reduced by using the principal component analysis and the classification of the dataset in to normal and attack classes is done by using Naïve Bayes Classifier. The experiments were conducted on the intrusion detection dataset called KDD’99 cup dataset. The comparison of the results with and without dimensionality reduction is also done.