Trust Computational Heuristic for Social Internet of Things: A Machine Learning-based Approach

Abstract

The Internet of Things (IoT) is an evolving network of billions of interconnected physical objects, such as, numerous sensors, smartphones, wearables, and embedded devices. These physical objects, generally referred to as the smart objects, when deployed in real-world aggregates useful information from their surrounding environment. As-of-late, this notion of IoT has been extended to incorporate the social networking facets which have led to the promising paradigm of the 'Social Internet of Things' (SIoT). In SIoT, the devices operate as an autonomous agent and provide an exchange of information and services discovery in an intelligent manner by establishing social relationships among them with respect to their owners. Trust plays an important role in establishing trustworthy relationships among the physical objects and reduces probable risks in the decision making process. In this paper, a trust computational model is proposed to extract individual trust features in a SIoT environment. Furthermore, a machine learning-based heuristic is used to aggregate all the trust features in order to ascertain an aggregate trust score. Simulation results illustrate that the proposed trust-based model isolates the trustworthy and untrustworthy nodes within the network in an efficient manner.

A Survey on Trust Models in Heterogeneous Networks

“…To solve the problem that indirect recommendations are not considered in [126], Sagar et al [187] regarded trust as direct trust and indirect trust, where direct trust is the weighted sum of friendship similarity, community of interest, cooperativeness and reward/punishment, and indirect trust is derived by other nodes. These features are employed as an input of ML models.…”

A Survey of Trust Management Schemes for Social Internet of Things

“…Sagar et al [14] proposed a computational trust model that extracted vital features viz., direct trust metrics and indirect trust metrics to compute trust in SIoT. The overall single trust score was computed for each node in the SIoT environment using a machine learning-based approach to classify a node as either trustworthy or otherwise.…”

“…Risk mitigation, authentication, security, and data transfer guarantee that IoT devices are approved. The concept of trust is identified as an immediate solution to help SIoT services to resolve the sense of uncertainty and reduce risks when making decisions [14]. Trust helps one measure trustworthiness, truthfulness, security, and reliability [8].…”

Understanding the Trustworthiness Management in the Social Internet of Things: A Survey

“…Consequently, there is a need of intelligent trust aggregation mechanism to overcome the limitations of conventional aggregation techniques. Lately, the idea of machine learning-based aggregation has been suggested by the researchers to obtain the weights of each metric in terms of its importance [112]. However, machine learning-based solutions have their own limitations, e.g., these solutions are computationally expensive and results in increasing the computational latency.…”