2021/02/03 by Subhash Sagar, Adnan Mahmood, Sagar, Subhash +7 · 1 citation
Computer Science · #Blockchain Technology Applications and Security #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #IoT and Edge/Fog Computing #Privacy-Preserving Technologies in Data #Social and Information Networks (cs.SI)
paper · pdf · doi:10.48550/arxiv.2102.10998
openalex publication_date 2021/02/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The emerging paradigm of the Social Internet of Things (SIoT) has transformed\nthe traditional notion of the Internet of Things (IoT) into a social network of\nbillions of interconnected smart objects by integrating social networking\nfacets into the same. In SIoT, objects can establish social relationships in an\nautonomous manner and interact with the other objects in the network based on\ntheir social behaviour. A fundamental problem that needs attention is\nestablishing of these relationships in a reliable and trusted way, i.e.,\nestablishing trustworthy relationships and building trust amongst objects. In\naddition, it is also indispensable to ascertain and predict an object's\nbehaviour in the SIoT network over a period of time. Accordingly, in this\npaper, we have proposed an efficient time-aware machine learning-driven trust\nevaluation model to address this particular issue. The envisaged model\ndeliberates social relationships in terms of friendship and community-interest,\nand further takes into consideration the working relationships and\ncooperativeness (object-object interactions) as trust parameters to quantify\nthe trustworthiness of an object. Subsequently, in contrast to the traditional\nweighted sum heuristics, a machine learning-driven aggregation scheme is\ndelineated to synthesize these trust parameters to ascertain a single trust\nscore. The experimental results demonstrate that the proposed model can\nefficiently segregates the trustworthy and untrustworthy objects within a\nnetwork, and further provides the insight on how the trust of an object varies\nwith time along with depicting the effect of each trust parameter on a trust\nscore.\n