Abstract:
Social IoT (or SIoT) is an alternate architectural pattern for IoT, which involves imparting social behavioral attributes to IoT devices. An SIoT service network uses social collaboration between IoT devices (acting as service users or service providers or both), enabling low-latency collaborative services and applications. A key challenge in implementing an SIoT service network in a multi-vendor network of heterogeneous IoT devices is the issue of Trust. The problem is in prioritization and selection of trustworthy service provider(s) in an autonomous and independent manner. In a single-vendor network, the problem is handled via proprietary methods that do not scale for multi-vendor environments. The problem is further compounded in networks having IoT devices that are constrained in computational and storage resources. In this paper, we propose the use of Neighborhood Overlap for estimating tie-strengths and the consequent prioritization of service providers based on the estimated tie-strength. We verify the relationship between neighborhood overlap and tie-strength using three publicly available datasets. While past research on neighborhood-overlap and its relationship with tie-strength focuses on undirected social networks only, we extend the definition of neighborhood-overlap for directed networks. We further prove this extension with the help of two publicly available directed social network datasets. The idea proposed in this paper is fundamental and can be extended towards defining a trust framework for SIoT.