AI-Driven Threat Intelligence in Cloud Computing Detecting and Responding to Cyber Attacks
A. Beatrice Dorothy, B. Madhavidevi, Balusamy Nachiappan, G. Manikandan, Pramod Kumar Patjoshi, M. Sindhuja · 2024
This research work tackles flaws in typical cloud threat intelligence systems, which often depend on static rules and signature-based detection approaches that are unable to react to changing cyber threats. These constraints highlight the need for a more proactive approach, leading the development of a novel system that incorporates AI-driven approaches. The work goes beyond static rule-based models and proposes an AI-driven method to addressing inadequacies in current systems. Combining anomaly detection and machine learning (ML) techniques enables the system to adapt to changing security threats. The first phases involve gathering and analyzing data from numerous cloud sources to improve the system's capacity to spot problems. Supervised learning with Random Forest classifies known hazards, while unsupervised learning with Isolation Forest detects new abnormalities. Real-time monitoring and response considerably improve the system's threat detection rates (95%), anomaly detection (93%), and other performance indicators. The proposed system surpasses the existing system by 95% accuracy, 93% precision, and 96% recall. These findings demonstrate how effectively the framework enables cloud safety and its capacity to enhance overall digital safety and proactively prevent assaults.