AI-EMPOWERED DATA SCIENCE FRAMEWORK FOR REAL-TIME CYBER THREAT DETECTION AND RESPONSE

Abstract

The increasing sophistication of cyber threats demands intelligent and real-time security solutions beyond traditional rule-based systems. This study presents an AI-empowered data science framework for real-time cyber threat detection and automated response in dynamic network environments. The proposed architecture integrates scalable big data processing, advanced feature engineering, and hybrid machine learning–deep learning models to detect both known and zero-day attacks with high accuracy and low latency. Experimental evaluation using benchmark cybersecurity datasets demonstrates improved detection performance, reduced false positives, and faster response times compared to conventional intrusion detection approaches. An intelligent response module further enables automated threat prioritization and containment, significantly enhancing security operations efficiency. The framework offers a scalable and adaptable solution for next-generation cybersecurity in cloud, edge, and enterprise infrastructures.