Indian Journal of Science and Technology
DOI: 10.17485/ijst/2016/v9i5/83656
Year: 2016, Volume: 9, Issue: 5, Pages: 1-8
Original Article
Preeti Aggarwal* and Deepak Dahiya
School of Engineering and Technology, Ansal University, Gurgaon - 122003, Haryana, India; preetaggarwal@gmail. com, [email protected]
*Author For Correspondence
Preeti Aggarwal School of Engineering and Technology, Ansal University, Gurgaon - 122003, Haryana, India; preetaggarwal@gmail. com
KDD Cup dataset has been key in studying the Intrusion Detection Systems whose attributes can be labeled in four classes. The objective of this study is to assimilate the contribution of attributes from each of these four classes in achieving high detection rate and low false alarm rate. Machine learning algorithms are employed to study the classification of KDD Cup dataset in two classes of normal and anomalous data. Different variants of KDD Cup dataset are created with respect to four labels and each of these variants is simulated on a set of same algorithms. The results derived from the study of each data variant is analyzed and compared to derive a broad conclusion. This pragmatic study compiles the findings for detection rate and false alarm rate in intrusion detection systems with respect to data under each of the four labels. The study contributes to the estimation of desired attributes for achieving maximum detection rate and minimum false alarm rate simultaneously while adhering to the earlier findings signifying the obligatory connection of basic labeled attributes in intrusion detection. The study can help reduce the data complexity while identifying major attributes of a particular label that are significant in getting high detection rate and low false alarm rate at the same time.
Keywords: Detection Rate, False Alarm Rate, Intrusion Detection System, KDD Cup Dataset, Machine Learning
Subscribe now for latest articles and news.