Intrusion Detection over Networking KDD Dataset using Enhance Mining Algorithm
Bhagwat P. Dwivedi1, Shiv Kumar2, Babita Pathik3
1Bhagwat P. Dwivedi, M.Tech. Scholar, Department of Computer Science and Engineering, Lakshmi Narain College of Technology Excellence, Bhopal (M.P)-462021, India.
2Dr. Shiv Kumar, Professor & Head, Department of Computer Science and Engineering, Lakshmi Narain College of Technology Excellence, Bhopal (M.P)-462021, India.
3Babita Pathik, Assistant Professor, Department of Computer Science and Engineering, Lakshmi Narain College of Technology Excellence, Bhopal (M.P)-462021, India.
Manuscript received on 10 December 2016 | Revised Manuscript received on 18 December 2016 | Manuscript Published on 30 December 2016 | PP: 79-82 | Volume-6 Issue-2, December 2016 | Retrieval Number: B4802126216/16©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The intrusion detection systems (IDSs) generate large number of alarms most of which are false positives. Fortunately, there are reasons for triggering alarms where most of these reasons are not attacks. In this research, a rule based technique which is the enhancement of genetic algorithm has been developed. For this, The networking data and intrusion over the data is find to extract to recognize various entities into it. Data mining and its algorithm to process, data extraction, and data analysis is an important phase to monitor the features in it. Intrusion detection process follows the clustering and classification technique to monitor the data flow in it. In this paper our investigation is about to observe available algorithm for the intrusion detection. Algorithm such as Genetic, SVM etc have been processed over KDD cup 10% of dataset which contain 41 attributes and large number of data availability. Here our experiment also conclude that the proposed feature extraction algorithm outperform as best than the existing algorithm with computation parameter such as precision, recall and its accuracy.
Keywords: Intrusion Detection, Clustering Technique, Data Mining, KDD.
Scope of the Article: Clustering