Trust Computational Model for IoT using Machine Learning

Abstract

Aims and Background: The Internet of Things has evolved over the years to a greater extent, where objects communicate with each other over a network. Heterogenous communication between the nodes leads to a large amount of information sharing, and sensitive information could be shared over the network. It is important to maintain privacy and security during information sharing to protect devices from communicating with malicious nodes. Objectives and Methodology: The concept of trust was introduced to prevent nodes from communicating with malicious nodes. A trust computation model for the IoT based on machine learning concepts was designed, which evaluates trust based on the Trust Marks. There are three trust marks, out of which two are evaluated. The three trust marks are knowledge, experience, and reputation. Knowledge trust marks are evaluated separately based on their trust property mathematical formulations, and then based on these properties, machine learning-based algorithms are applied to train the model to classify the objects as trustworthy and untrustworthy. Results: The effectiveness of the Knowledge Trust Mark is measured by a simulation and confusion matrix. The accuracy of the trained model is shown by the accuracy score. The trust computational model for IoT using machine learning shows higher accuracy in classifying the objects as trustworthy and untrustworthy. Conclusion: The experience trust mark is evaluated based on its properties, and the behaviour of the experience is shown over time graphically.