Published January 1, 2020 | Version v1

Cloud Security Monitoring Using AI-Based Analytics

Authors/Creators

Description

The rapid migration of enterprise workloads to the cloud has expanded the cyber-attack surface, rendering traditional rule-based security monitoring tools largely ineffective against sophisticated, polymorphic threats. This review examines the integration of artificial intelligence (AI) and machine learning (ML) within cloud security frameworks to enhance real-time threat detection and response. We analyze the evolution from signature-based systems to behavior-centric analytics, highlighting the role of Deep Learning (DL), Convolutional Neural Networks (CNNs), and Federated Learning in securing multi-tenant environments. The article discusses how AI-driven Security Orchestration, Automation, and Response (SOAR) platforms have reduced incident response times by up to 60% (Almadhoun et al., 2021). Despite these advancements, significant hurdles remain, including the \\\"black-box\\\" nature of deep learning models, data privacy constraints under regulations like GDPR, and the rise of adversarial AI. This study concludes by identifying future research directions, emphasizing Explainable AI (XAI) and autonomous self-healing cloud architectures as the next frontier in digital resilience.

Files

IJSET_V8_issue2_206.pdf

Files (437.9 kB)

Name Size
md5:cfa3aea4eea80e5b3d79c5fbd0b8c229
437.9 kB Preview Download

Additional details