Enhancing Cloud Security with Machine Learning-Based Anomaly Detection

Aisha, Mohammed and Theresa Ojevwe, Akroh and Chinwe Sheila, Nwachukwu (2025) Enhancing Cloud Security with Machine Learning-Based Anomaly Detection. American Journal of Engineering, Mechanics and Architecture, 3 (3). pp. 51-68. ISSN 2993-2637

Text 51-68+Enhancing+Cloud+Security+with+Machine+.pdf Download (553kB)

Abstract

With the increasing adoption of cloud computing across industries, ensuring robust security measures has become a critical priority. Traditional security approaches, such as rule-based intrusion detection systems and signature-based methods, often fail to detect novel and sophisticated cyber threats in real-time. As a result, the integration of machine learning (ML) for anomaly detection has emerged as a powerful solution for enhancing cloud security. This paper explores the implementation of ML-based anomaly detection techniques to identify and mitigate security threats in cloud environments. Specifically, it examines various ML approaches, including supervised, unsupervised, and reinforcement learning, and their effectiveness in detecting deviations from normal system behavior. By analyzing patterns in network traffic, user activity, and system logs, ML models can identify potential threats such as insider attacks, unauthorized access, malware infiltration, and distributed denial-of-service (DDoS) attacks.

Item Type:	Article
Subjects:	Q Science > Q Science (General)
Divisions:	Postgraduate > Master's of Islamic Education
Depositing User:	Journal Editor
Date Deposited:	10 Mar 2025 11:22
Last Modified:	10 Mar 2025 11:22
URI:	http://eprints.umsida.ac.id/id/eprint/15809

Actions (login required)

View Item