An Adaptive Fuzzy SIR Model for Real-Time Malware Spread Prediction in Industrial Internet of Things Networks

Abstract

The Industrial Internet of Things (IIoT) networks serve as the foundational infrastructure for real-time communication and data exchange in smart manufacturing. Predicting the spread of malware within IIoT networks is particularly challenging due to uncertainties in infection and recovery rates, which are influenced by dynamic network conditions and device heterogeneity. In this article, we propose an adaptive fuzzy SIR model that incorporates fuzzy logic and gradient descent optimization to address these uncertainties. Specifically, we integrate fuzzy logic with gradient descent, which introduces an adaptive mechanism to handle uncertain infection and recovery rates in real time. This synergy ensures robust parameter tuning under fluctuating network states, significantly improving malware spread prediction. The proposed model dynamically adjusts infection and recovery rates using fuzzy differential equations and real-time data adaptation, enhancing prediction accuracy and resilience to network fluctuations. Experimental results demonstrate the model’s advantages in improving predictive accuracy, convergence speed, and adaptability, making it a robust solution for securing IIoT networks in smart manufacturing.