A Secured Industrial Internet-of-Things Architecture Based on Blockchain Technology and Machine Learning for Sensor Access Control Systems in Smart Manufacturing

In this paper, a layered architecture incorporating Blockchain technology (BCT) and Machine Learning (ML) is proposed in the context of Industrial Internet-of-Things (IIoT) for smart manufacturing applications. The composed five layers covering sensing, network/protocol, transport enforced with BCT components, application advanced services (i.e., data, ML cloud) layers. enables gathering sensor access control information, while brings its effectivity attack detection such as DoS (Denial Service), DDoS (Distributed Denial injection, man middle (MitM), brute force, cross-site scripting (XSS) scanning attacks by employing classifiers differentiating between normal malicious activity. design our compared to similar ones literature point out potential benefits. Experiments, based on IIoT dataset, have been conducted evaluate contribution, using four metrics: Accuracy, Precision, Sensitivity Matthews Correlation Coefficient (MCC). Artificial Neural Network (ANN), Decision Tree (DT), Random Forest, Naive Bayes, AdaBoost Support Vector (SVM) are evaluated regarding these metrics. Even if more experiments required, it illustrated that can reduce significantly number DDoS, force XSS threats within an framework networks contract along classifiers.