Adaptive Edge-Cloud Intelligence for Secure Industrial Automation: Integrating AI-Based Threat Detection, Cryptographic Data Protection, and Optimization-Driven Resource Management

Abstract

The rapid evolution of the Industrial Internet of Things (IIoT), Industry 4.0/5.0, and intelligent manufacturing has increased the demand for secure, low-latency, and adaptive computing infrastructures capable of processing large volumes of distributed industrial data. Conventional cloud-centric architectures often face challenges related to communication latency, bandwidth limitations, and centralized security risks. Edge-cloud intelligence addresses these challenges by combining the low-latency processing capabilities of edge devices with the scalability of cloud computing. However, integrating AI-based threat detection, cryptographic data protection, and intelligent resource management into a unified framework remains a significant challenge. This study proposes an adaptive edge-cloud intelligence framework for secure industrial automation that integrates machine learning-based threat detection, lightweight cryptographic protection, and optimizationdriven resource management. The framework is designed to improve cybersecurity, computational efficiency, resource utilization, and system scalability while supporting secure data exchange across heterogeneous IIoT environments. Performance is evaluated using metrics including threat detection accuracy, communication latency, encryption overhead, resource utilization, and scalability. The proposed framework is expected to enhance operational resilience, reduce security risks, and support efficient, secure, and intelligent industrial automation for next-generation Industry 5.0 applications.