Enhancing performance of anomaly based intrusion detection systems through dimensionality reduction using principal component analysis

Anomaly based Intrusion Detection Systems (IDSs) are capable of detecting wide range of network attacks. However, they are characterized by high computational overhead due to large number of redundant or highly correlated features in the input data being analyzed by them. In this paper, we propose a model to minimize the computational overhead of anomaly based IDSs through dimensionality reduction technique called Principal Component Analysis (PCA). PCA reduces the high dimensional data using the dependencies between the input features to represent it in a more tractable, lower dimensional form, without losing any significant information contained in the original data. Experimental results on the benchmark NSL-KDD dataset shows that applying PCA can significantly reduce the dimensionality of the data being processed by anomaly based IDSs and thereby minimize their computational overhead without adversely affecting their performances.