Guarding the Cloud - An Effective Detection of Cloud-Based Cyber Attacks using Machine Learning Algorithms

Aug 4, 2026

Cloud computing has become widely adopted because it delivers reliability and scalability, but it also introduces security risks alongside dependencies such as connectivity and operational downtime. This paper addresses guarding the cloud by focusing on two common cloud threats: Distributed Denial-of-service (DDoS) and Man-in-the-Cloud (MitC) computing attacks. Machine learning methods including Decision Trees, Support Vector Machine (SVM), Naive Bayes, and K-Nearest Neighbors (KNN) are applied to detect malicious behavior. Simulated attacks generate datasets used for training and evaluation, and results show strong capability to distinguish malicious activity from legitimate network traffic, with Decision Trees showing the most promising performance.

LanguageEnglish

CategoryTechnology

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Introduction

Background and cloud computing characteristics

Cloud security challenges and common attacks

Methodology

Attack scenarios and dataset preparation

Machine learning algorithms used

Experimental Results

Detection and classification performance

Conclusion

Decision Trees effectiveness and mitigation impact

JOE International Journal of Online and Biomedical Engineering [Onli](Online-Journals.org)[ne-Jo](Online-Journals.org)[urnals](Online-Journals.org)[.org](Online-Journals.org) iJOE | eISSN: 2626-8493 | Vol. 19 No. 18 (2023) | [https://doi.org/10.3991/ijoe.v19i18.45483](https://doi.org/10.3991/ijoe.v19i18.45483) PAPER Guarding the Cloud: An Effective Detection of Cloud-Based Cyber Attacks using Machine Learning Algorithms Blerim Rexha1, Rrezearta Thaqi1(􀀍), Artan Mazrekaj1, Kamer Vishi2 1Faculty of Electrical and Computer Engineering, University of Prishtina, Prishtina, Kosovo 2Department of Informatics, University of Oslo, Oslo, Norway [rrezearta.thaqi@uni-pr.edu](rrezearta.thaqi@uni-pr.edu) ABSTRACT Cloud computing has gained significant popularity due to its reliability and scalability, making it a compelling area of research. However, this technology is not without its challenges, including network connectivity dependencies, downtime, vendor lock-in, limited control, and most importantly, its vulnerability to attacks. Therefore, guarding the cloud is the objective of this paper, which focuses, in a novel approach, on two prevalent cloud attacks: Distributed Denial-of-service (DDoS) attacks and Man-in-the-Cloud (MitC) computing attacks. To tackle the detection of these malicious activities, machine learning algorithms, namely Decision Trees, Support Vector Machine (SVM), Naive Bayes, and K-Nearest Neighbors (KNN), are utilized. Experimental simulations of DDoS and MitC attacks are conducted within a cloud environment, and the resultant data is compiled into a dataset for training and evaluating the machine learning algorithms. The study reveals the effectiveness of these algorithms in accurately identifying and classifying malicious activities, effectively distinguishing them from legitimate network traffic. The finding highlights Decision Trees algorithm with most promising potential of guarding the cloud and mitigating the impact of various cyber threats. KEYWORDS cloud computing, decision trees, support vector machine, naive bayes, k-nearest neighbors, machine learning, attacks, security 1 INTRODUCTION Over the past years, cloud computing has been one of the most popular and fast growing technologies. It provides a range of different services for various applications such as data storage, servers, databases, networking, and software [1] . As it is combined by Internet, distributed systems and virtualization, it allows the users Rexha, B., Thaqi, R., Mazrekaj, A., Vishi, K. (2023) . Guarding the Cloud: An Effective Detection of Cloud-Based Cyber Attacks using Machine Learning Algorithms. International Journal of Online and Biomedical Engineering (iJOE), 19(18), pp. 158–174. [https://doi.org/10.3991/ijoe.v19i18.45483](https://doi.org/10.3991/ijoe.v19i18.45483)[ ](https://doi.org/10.3991/ijoe.v19i18.45483)[Article submitted 2023-09-07. Revision uploaded 2023-10-24. Final acceptance 2023-10-26.](Article submitted 2023-09-07. Revision uploaded 2023-10-24. Final acceptance 2023-10-26.) © 2023 by the authors of this article. Published under CC-BY. 158 International Journal of Online and Biomedical Engineering (iJOE) iJOE | Vol. 19 No. 18 (2023) Guarding the Cloud: An Effective Detection of Cloud-Based Cyber Attacks using Machine Learning Algorithms to access the information technology infrastructure and applications on demand through the Internet. Compared to locally deployed information technology applications and solutions, cloud computing is characterized by virtualization, dynamic and high scalability, on-demand deployment, and high flexibility. Cloud computing has changed the understanding and functionality of the applications. This includes stronger computing power at a lower cost and also the combination with artificial intelligence, Internet of Things, and machine learning to enhance the scope of applications. The growth in cloud-enabled services and cloud market is unprece

FAQs

Which two cloud attacks does the paper focus on for detection?

The paper focuses on Distributed Denial-of-service (DDoS) attacks and Man-in-the-Cloud (MitC) computing attacks.

Which machine learning algorithms are used to detect malicious cloud activity?

Decision Trees, Support Vector Machine (SVM), Naive Bayes, and K-Nearest Neighbors (KNN) are used for detection and classification.

How is the dataset for training and evaluation created?

Experimental simulations of DDoS and MitC attacks are conducted in a cloud environment, and the resulting data are compiled into a dataset for training and evaluating the algorithms.

Aug 4, 2026

Upload by Ava Thompson