Abstract
The IoT has gained significant recognition from research and industrial communities over the last decade. The concept of Industrial IoT (IIoT) has emerged to improve industrial processes and reduce downtime or breach in secure communication. If automated, industrial applications can make the implementation process more convenient, it also helps increase productivity, but an external attacker may cause distortion to the process, which could cause much damage. Thus, a trust management technique is proposed for securing IIoT. The transition of the Internet to IoT and for industrial applications to IIoT leads to numerous changes in the communication processes. This transition was initiated by wireless sensor networks that have unattended wireless topologies and were comprised due to the nature of their resource-constrained nodes. In order to protect the sensitivity of transmitted information, the security protocol uses the Datagram Transport Layer Security (DTLS) mandated by Secure Constrained Application Protocol (CoAP). However, DTLS was designed for powerful devices and needed strong support for industrial applications connected through high-bandwidth links. In the proposed trust management system, machine learning algorithms are used with an elastic slide window to handle bigger data and reduce the strain of massive communication. The proposed method detected on and off attacks on nodes, malicious nodes, healthy nodes, and broken nodes. This identification is necessary to check if a particular node could be trusted or not. The proposed technique successfully predicted 97% of nodes' behavior faster than other machine learning algorithms.