Intrusion Detection System for Cloud using Machine Learning

In this document, a Machine Learning-driven Intrusion Detection System (IDS) tailored for cloud computing environments has been introduced to tackle the increasing security issues linked to cloud infrastructure. The system employed feature selection methods and classification algorithms, including Random Forest and Support Vector Machine, to effectively identify malicious activities. Experimental findings indicated that the proposed model attained high accuracy, enhanced detection rates, and minimized false alarm rates in comparison to conventional IDS methodologies. The research emphasizes the significance of incorporating Machine Learning methodologies into intrusion detection systems to improve their capacity to identify both recognized and unrecognized attacks. The application of feature selection additionally enhanced system efficiency by minimizing data complexity and processing duration. Among the assessed models, Random Forest demonstrated exceptional performance, rendering it an appropriate option for cloud-based IDS implementations.

[1] S. Lata and D. Singh, "Intrusion Detection System in Cloud Environment: Literature Survey and Future Research Directions," International Journal of Information Management Data Insights, vol. 2, no. 2, 2022. [2] H. Attou, A. Khoumsi, and S. E. Ouatik, "A Cloud-Based Intrusion Detection System Using Machine Learning," Journal of Cloud Computing, 2023. [3] Z. Li, A. L. G. Rios, and G. Xu, "A Review of Deep Learning-Based Intrusion Detection Systems for Network Security," IEEE Access, vol. 8, pp. 1–15, 2020. [4] M. Tavallaee, E. Bagheri, W. Lu, and A. A. Ghorbani, "An In-Depth Examination of the KDD CUP 99 Data Set," presented at the IEEE Symposium on Computational Intelligence for Security and Defense Applications, 2009. [5] M. Sharafaldin, A. H. Lashkari, and A. A. Ghorbani, "Towards the Creation of a Novel Intrusion Detection Dataset and Characterization of Intrusion Traffic," presented at the ICISSP, 2018. [6] L. Breiman, "Random Forests," Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. [7] C. Cortes and V. Vapnik, "Support Vector Networks," Machine Learning, vol. 20, no. 3, pp. 273–297, 1995. [8] S. Mukkamala, G. Janoski, and A. Sung,    "Intrusion Detection Utilizing Neural Networks and Support Vector Machines," presented at the Proc. IEEE International Joint Conference on Neural Networks, 2002. [9] W. Stallings, Cryptography and Network Security: Principles and Practice, 7th edition, Pearson, 2017. [10] N. Moustafa and J. Slay, "UNSW-NB15: An Extensive Data Set for Network Intrusion Detection Systems," presented at the Military Communications and Information Systems Conference, 2015.