Predictive Modeling for Attack Classification using Optimized Naïve Bayes using Weka
Amrin Mansoori1, Ankita Hundet2, Babita Pathik3, Shiv Kumar4
1Amrin Mansoori, M.Tech Scholar, Department of Computer Science & Engineering, Lakshmi Narain College of Technology & Excellence, Bhopal (M.P), India.
2Ankita Hundet, Assistant Professor, Department of Computer Science & Engineering, Lakshmi Narain College of Technology & Excellence, Bhopal (M.P), India.
3Babita Pathik, Assistant Professor, Department of Computer Science & Engineering, Lakshmi Narain College of Technology & Excellence, Bhopal (M.P) India.
4Dr. Shiv Kumar, Professor & Head, Department of Computer Science & Engineering, Lakshmi Narain College of Technology & Excellence, Bhopal (M.P), India.
Manuscript received on 02 November 2017 | Revised Manuscript received on 21 November 2017 | Manuscript Published on 30 December 2017 | PP: 8-13 | Volume-7 Issue-2, November 2017 | Retrieval Number: J24420661017/2017©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 information security research that has been the subject of much attention in recent years is that intrusion detection systems. Intrusion-detection systems (IDS) intend at detecting attacks against computer systems and networks or, in general, against information systems. In fact, it is difficult to provide efficient IDS and to maintain them in such a secure state during their lifetime and utilization. Intrusion–detection systems have the task of detection of any insecure states. Machine learning in data mining field plays an essential role in the Network Intrusion Detection research area. Although there are several technological advancements in field of IDS still there are challenges. IDS are intended at detecting attacks against computer systems and networks or, in general, against information systems. The problem of developing an ability to detect novel attacks or unknown attacks based on audit data in IDS is still on verge. Also, the classification accuracy is one such inadequacy, the Weka tool is tested for the few machine learning techniques in this work. This paper presents comparison of KNN, Decision tree, Naïve Bayes based classifiers using Weka tool, for IDS. This paper will provide an insight for the future research. The KDD CUP’99 data set is employed for experiment, result analysis and evaluation. The methods tested based on Detection rate and False Alarm rate.
Keyword: Classification, Data Mining, Intrusion Detection System (IDS), Machine Learning techniques, Weka, KDD CUP’99 dataset
Scope of the Article: Classification