Network Malware Detection using Soft Computing and Machine Learning Techniques
Yogita R. Kulkarni1, Sandeep A. Thorat2
1Yogita R. Kulkarni, Department of Computer Engineering, Rajarambapu Institute of Technology, Rajaramnar, India.
2Dr. Sandeep A. Thorat, Department of Computer Engineering, Rajarambapu Institute of Technology, Rajaramnar, India.
Manuscript received on November 26, 2019. | Revised Manuscript received on December 15, 2019. | Manuscript published on December 30, 2019. | PP: 879-885 | Volume-9 Issue-2, December, 2019. | Retrieval Number: A1654109119/2020©BEIESP | DOI: 10.35940/ijeat.A1654.129219
Open Access | Ethics and Policies | Cite | Mendeley
© 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: In today’s world there is rapid increase in the information which makes addressing of security issues more important. Malware detection is an important area for research in effective and secure functioning of computer networks. Research efforts are required to protect the systems from various security attacks. In this paper, we analyze usefulness of Soft Computing and Machine Learning Techniques for network malware detection. Hamamoto et al. [1] used combination of Genetic Algorithm and Fuzzy logic for implementation of network anomaly detection. The research work proposed in this paper extends the concepts discussed in [1]. The proposed work explores use of various Machine Learning algorithms such as K-Nearest Neighbor, Naïve Bayes and Decision Tree for network anomaly detection. The experimental observations are conducted on CIDDS (Coburg Intrusion Detection Data Set) dataset [14]. It is observed that Decision Tree approach gave better results as compared to KNN and Naïve Bayes techniques. Decision Tree technique gives 99% of accuracy and precision of 1 and recall of 1.
Keywords: Network Malware Detection, Soft Computing, Machine Learning, K-Nearest Neighbors, Naïve Bayes, Decision Tree.