Enhancing Cloud Vulnerability Management Using Machine Learning: Advancing Data Privacy and Security in Modern Cloud Environments
Year: 2024
Type: article
Abstract: In today’s rapidly evolving cloud environments, managing vulnerabilities and data privacy is a critical challenge due to the increasing complexity and volume of data. Traditional methods of vulnerability detection and management often fall short in addressing the dynamic nature of cloud workloads, leading to missed critical vulnerabilities and delays in notifying the right stakeholders and incident responses. This paper presents a machine learning-based approach to enhance cloud vulnerability management, focusing on the detection, classification, and prioritization of vulnerabilities in real-time. Using a dataset of 500,000 security logs and vulnerability reports, the proposed model achieved a 92% accuracy in predicting vulnerabilities, with a 94% recall and a 91.5% F1 score. The model demonstrated its effectiveness by reducing false positives to 2% and reducing incident response times by 30%. Additionally, it optimized resource utilization by 20% and led to an estimated 15% reduction in operational security costs. The results underscore the potential of machine learning to improve the efficiency and effectiveness of cloud vulnerability management significantly, and this will help us reduce risk and safeguard data, providing a scalable and adaptive solution to reduce risk in modern cloud infrastructures.
Authors: Satyanarayana Raju, Dorababu Nadella
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4403514602