ARCHIVES

Wireless sensor networks form the backbone of Industry 4.0 environments, enabling continuous data flow and automated decision-making. Their openness, however, exposes them to evolving cybersecurity risks. This work presents an enhanced situation-driven framework that not only detects intrusions using machine learning and deep learning models but also analyzes and interprets attack behavior through an integrated analytics console. The system incorporates features such as prediction history tracking, attack-specific behavioral insights, packet-loss visualizations, severity scoring, and timeline-based threat progression to support informed decision-making. Along with identifying attacks such as blackhole, grayhole, flooding, and TDMA violations, the framework offers prevention capabilities including automated mitigation, policy-based controls, and model-management functions. Experimental evaluation on benchmark datasets demonstrates strong accuracy and reliable attack characterization. The overall approach supports scalable, context-aware defense strategies suitable for modern industrial networks.