IJBTT

A Hybrid Machine Learning-Based Approach for Dynamic Identification of Network Attacks in Cloud Environment

A Hybrid Machine Learning-Based Approach for Dynamic Identification of Network Attacks in Cloud Environment
	International Journal of Engineering Trends and Technology (IJETT)
	© 2022 by IJETT Journal
	Volume-70 Issue-3
	Year of Publication : 2022
	Authors : Madhura S. Mulimani, Rashmi R. Rachh, Shridhar Allagi
	https://doi.org/10.14445/22315381/IJETT-V70I3P205

How to Cite?

Madhura S. Mulimani, Rashmi R. Rachh, Shridhar Allagi, "A Hybrid Machine Learning-Based Approach for Dynamic Identification of Network Attacks in Cloud Environment," International Journal of Engineering Trends and Technology, vol. 70, no. 3, pp. 37-47, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I3P205

Abstract
The exponential evolution of the network and development of various technologies has led to an exponential increase in connected devices and users. While users can conveniently leverage the network services and resources, the ever-increasing number of users and resources has escalated the extent of various types of attacks which may have detrimental consequences in the network when left undetected or untreated. Traditional cybersecurity systems that use static methods are inadequate in coming up with rules for emerging threats or zero-day attacks and also lack the scalability with the increasingly complex cyberspace landscape. In recent times, machine learning techniques have gained a lot of attraction due to their potential in learning and making accurate predictions. In the considered work, numerous machine learning techniques have been comprehensively explored to recognize different types of attacks as well as to classify them. In the experiments, base classifiers such as Logistic Regression, Decision-Tree, Neural Network, Naïve-Bayes, and Support Vector Machine have been used to identify the attacks. To further boost the model’s performance, ensemble learning models have been used. Additionally, the unsupervised method has been used. The experiment has been conducted using the NSL-KDD dataset to provide a detailed performance analysis of various machine learning techniques.

Keywords
Cybersecurity, Ensemble Machine Learning, K-means, Machine learning, NSL-KDD Dataset.

Reference
[1] S. Choudhary and A. Sharma, Malware Detection Classification using Machine Learning, Proc. - 2020 Int. Conf. Emerg. Trends Commun. Control Comput. ICONC3 ,(2020) 20–23.
[2] Y. Zhou, G. Cheng, S. Jiang, and M. Dai, Building an Efficient Intrusion Detection System based on Feature Selection and Ensemble Classifier, Comput. Networks,174(8) (2020) 1–12.
[3] R. Patil, H. Dudeja, and C. Modi, Designing in-VM-assisted Lightweight Agent-Based Malware Detection Framework for Securing Virtual Machines in Cloud Computing, Int. J. Inf. Secur., 19(2) (2020) 147–162.
[4] B. I. Seraphim, S. Palit, K. Srivastava, and E. Poovammal, Implementation of Machine Learning Techniques Applied to the Network Intrusion Detection System, Int. J. Eng. Adv. Technol., 8(5) (2019) 2721–2726.
[5] S. Talukder, Tools and Techniques for Malware Detection and Analysis, (2020). [Online]. Available: http://arxiv.org/abs/2002.06819.
[6] S. Agarkar and S. Ghosh, Malware Detection and Classification using Machine Learning, Proc. - 2020 IEEE Int. Symp. Sustain. Energy, Signal Process. Cyber Secur. iSSSC 2020 (2020).
[7] A. Meryem and B. EL Ouahidi, Hybrid Intrusion Detection System using Machine Learning, Netw. Secur., 5 (2020) 8–19.
[8] X. Dong, Z. Yu, W. Cao, Y. Shi, and Q. Ma, A Survey on Ensemble Learning, Front. Comput. Sci., 14(2) (2020) 241–258.
[9] S. A. Ludwig, Applying a Neural Network Ensemble to Intrusion Detection, J. Artif. Intell. Soft Comput. Res., 9(3) (2019) 177–188.
[10] J. Gu, L. Wang, H. Wang, and S. Wang, A Novel Approach to Intrusion Detection using SVM Ensemble with Feature Augmentation, Comput. Secur., 86 (2019) 53–62.
[11] H. Rajadurai and U. D. Gandhi, A Stacked Ensemble Learning Model for Intrusion Detection in Wireless Network, Neural Comput. Appl., 5 (2020).