A Machine Learning-Based Trust Computational Heuristic for the SIoT Network

Trust plays an important role in establishing trustworthy relationships among the SIoT objects/nodes and reduces probable risks in the decision making process. Accordingly, this chapter aims to design a trust computational heuristic by employing a number of trust features including but not limited to friendship similarity, community-of-interest, cooperativeness, and reward/punishment as the direct perception (i.e., direct trust), whereas the indirect trust (recommendations) are utilized as the direct trust of friends of trustor towards a trustee. Furthermore, a machine learning-based heuristic is used to aggregate all the trust features in order to ascertain an aggregate trust score instead of a weighted sum approach as compared to the previous chapter (i.e., Chap. 2 ). Our simulation results illustrate that the proposed trust-based model isolates the trustworthy and untrustworthy nodes within the network in an efficient manner.