CYBERSHIELD-IIOT: A TRUST-CENTRIC DEEP LEARNING MODEL FOR INTELLIGENT ATTACK DETECTION IN SMART INDUSTRIES

Abstract

The rapid proliferation of Industrial Internet of Things (IIoT) systems has revolutionized manufacturing, logistics, and smart infrastructure by enabling seamless connectivity and automation. However, this increased interconnectivity exposes IIoT networks to diverse and sophisticated cyber threats, ranging from Distributed Denial of Service (DDoS) to data manipulation and unauthorized access. Traditional security mechanisms often fail to ensure reliability, scalability, and trustworthiness in such dynamic industrial environments. This paper presents CyberShield-IIoT, a trust-centric deep learning framework designed for intelligent cyberattack detection and prevention in industrial networks. The proposed system integrates Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks to capture both spatial and temporal features of network traffic, while a Trust Evaluation Layer dynamically scores device behaviors based on past reliability. Experiments conducted on benchmark IIoT datasets demonstrate that CyberShield-IIoT achieves superior accuracy, reduced false alarm rates, and higher adaptability compared to existing intrusion detection systems, ensuring a robust and trustworthy industrial security ecosystem