Author : Priyanka Alekar 1
Date of Publication :7th November 2018
Abstract: The intrusion detection systems are developed in order to monitor the network activity and tack the malicious interruption in network. In this context the generated traffic data is need to be analyzed. In most of the IDS design for traffic data analysis machine learning and data mining algorithms are utilized. These algorithms are able to deal with the data for discovering the valuable or target patterns from data. But in network the data is generated and communicated in a small amount of time and the algorithms consumes a significant amount of time. In this context different feature selection approaches are implemented with the IDS systems which reduce the dimensions of the data. With the fewer amounts of data attributes learning algorithms are trained well but detection performance can be affected. On the other hand for efficient computing and dealing with large amount of data the cloud computing is used. The cloud computing provides scalable resources and efficient computing methodology for process the data is fewer amount of time. Therefore in this presented work both the computing techniques namely cloud computing and data mining both are used for improving the performance and working of traditional IDS systems. The proposed data model works in client server architecture where the server performs the computations and produces the decision by analysis of client submitted traffic samples. For training and testing of data model the SVM (support vector machine) and BPN (back propagation neural network) is used. Additionally for experimentation the KDD CUP data is consumed. The experimental results show the proposed technique reduces the overhead of client end computing efforts and enhance the decision capability of IDS systems.
- Suraj Pandey, Kapil Kumar Gupta, Adam Barker, Rajkumar Buyya, “Minimizing Cost when using Globally Distributed Cloud Services: A Case Study in Analysis of Intrusion Detection Workflow Application”, http://citeseerx.ist.psu.edu/viewdoc/download? doi=10.1.1.151. 6055& rep=rep1&type=pdf
- Foster, Z. Yong, I. Raicu, and S. Lu, "Cloud Computing and Grid Computing 360-Degree Compared," in Grid Computing Environments Workshop, 2008. GCE '08, 2008, pp. 1-10
- “Introduction to Cloud Computing”, Dialiogic, available online at: https://www.dialogic.com/~/media/products/doc s/whitepapers/12023-cloud-computing-wp.pdf
- Carroll, Mariana, Alta Van Der Merwe, and Paula Kotze, "Secure cloud computing: Benefits, risks and controls", In Information Security South Africa (ISSA), 2011, pp. 1-9. IEEE, 2011.
- Introduction to Data Mining and Knowledge Discovery, Dunham, M. H., Sridhar, S., “Data Mining: Introductory and Advanced Topics”, Pearson Education, New Delhi, 1st Edition, 2006.
- Phridvi Raj MSB., GuruRao CV (2013) Data mining – past, present and future – a typical survey on data streams. INTER-ENG Procedia Technology 12, pp. 255 – 263
- Veepu Uppal and Gunjan Chindwani, “An Empirical Study of Application of Data Mining Techniques in Library System”, International Journal of Computer Applications (IJCA), Volume 74– No.11, July 2013.