International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Cloud Security through Adaptive Machine Learning for Real-Time Threat Detection |
|---|---|
| ABSTRACT | The rapid adoption of cloud computing across industries has revolutionized the digital ecosystem but simultaneously introduced complex security challenges. Cloud environments are inherently dynamic, characterized by distributed architectures, short-lived resources, and variable workloads. Traditional static and signature-based security systems have become inadequate in defending against evolving real-time cyberattacks. With adversaries leveraging advanced techniques such as polymorphic malware, intelligent intrusion, and automated attack frameworks, the need for intelligent, scalable, and adaptive security solutions has become critical. Adaptive Machine Learning (AML) frameworks offer a promising approach by enabling real-time detection and response through continuous learning and adaptation to changing patterns, behaviors, and threats in cloud environments. This paper provides an in-depth exploration of AML techniques for cloud security, focusing on key components such as incremental learning, online learning, ensemble modeling, and drift detection—capabilities that allow AML systems to remain resilient against both known and emerging risks. The study also examines major challenges in implementing AML, including concept drift, high false-positive rates, data privacy concerns, and scalability constraints. Furthermore, it discusses industry trends and opportunities, such as federated learning and explainable AI, while highlighting future research directions, including the potential role of quantum-enhanced machine learning in cybersecurity. The findings emphasize that AML is no longer merely a reactive safeguard but a proactive and essential element in protecting modern cloud architectures against an ever-evolving cyber threat landscape. |
| TITLE | |
| AUTHOR | J. SUGANYA, M. NITHYA, R. SHANMUGAPRIYA, P. AKILANDESWARI |
| VOLUME | 176 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1311045 |
| pdf/45_Cloud Security through Adaptive Machine Learning for Real-Time Threat Detection.pdf | |
| KEYWORDS |
