A Zero-Trust Network-Based Access Control Scheme for Sustainable and Resilient Industry 5.0

Abstract

This new era of the industry is characterized by the integration of artificial intelligence and the Internet of Things (IoT) to optimize production processes. To ensure sustainability and continuous industrial performance, Industry 5.0 integrates automated technology, robots, humans, and others. This modern paradigm relies on data and high-level security to achieve sustainability and error-free production operations. For improving the resilience of Industry 5.0 through adversary mitigation, this manuscript introduces a Zero-Trust Network-based Access Control Scheme (ZTN-ACS). This scheme extends its remote and limitless support for managing, monitoring, and controlling devices and operation schedules. For its limiting network over the available controllers, deep learning aids access control. The industrial controller output over the defined access is verified for efficiency and consistency compared to the expected and previous production outputs. In the verification scheme, access interrupts the controllers, and the schedules are initiated using the learning paradigm. This learning process considers the achievable production outcome and the low or high variations in the current access-based output. Therefore, the access control and security features are extended depending on the learning output over the adversaries. This scheme leverages consistency and reduces controller denials, failures, and false positives in Industry 5.0.

Keywords

• Access control
• deep learning
• Industry 5.0
• zero-trust