Intrusion Detection System Based on Principal Component Analysis and Machine Learning Techniques

  Sujata Chakravarty,  Nitu Dash,  Amiya Kumar Ratha

Intrusion is widely recognized as a chronic and recurring problem of computer systems security. Its growth changes continuously with the increasing volume of hacking techniques. In this paper, machine learning has been used to develop an intrusion detection system (IDS) that can effectively distinguish between normal and intrusive traffic. The system explores two different Neural Network techniques i.e. Multilayered Perceptron (MLP) and Radial Basis Function (RBF). The well-known gradient descent Backpropagation learning algorithm optimizes the parameters of the model. NSL KDD dataset is used for experimental work. One of the major problems faced by the researchers to develop IDS is large dimensionality of the datasets. In this study, Principal Component Analysis (PCA) has been used to reduce the curse of dimensionality and increase the computational efficiency. A number of useful performance evaluation measures including accuracy, sensitivity, specificity and confusion matrix are considered to examine the efficiency of the model. The results show that the feature subset obtained from PCA gives a higher detection and accuracy rate with a lower false alarm rate when compared with the obtained results using all features. Secondly, RBF based intrusion detection system gives more accuracy as compared with MLP. Thus, RBFIDS can be effectively used in the real life applications.

Keywords- Intrusion Detection System (IDS); Principal Component Analysis (PCA), Multilayered Perceptron (MLP); Backpropagation Learning algorithm; Radial Basis Function (RBF).

Unique Identification Number - IJEDR1803064
Page Number(s) - 359-367
Pubished in - Volume 6 | Issue 3 | August 2018
DOI (Digital Object Identifier) -    http://doi.one/10.1729/Journal.19301
Publisher - IJEDR (ISSN - 2321-9939)

  Sujata Chakravarty,  Nitu Dash,  Amiya Kumar Ratha,   "Intrusion Detection System Based on Principal Component Analysis and Machine Learning Techniques", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.6, Issue 3, pp.359-367, August 2018, Available at :http://www.ijedr.org/papers/IJEDR1803064.pdf