Differentially Privacy-preserving Social IoT

With the sophisticated network infrastructure, the breadth of Open Data and the increased smartphones, the popularity of the IoT (Internet of Things) has risen sharply. The Internet of Things bridges the gap between the physical world and the virtual world. The Internet of Things provides intelligent data services to humans through the integration of physical objects and information networks. The impact of users' social connections and interactions on the Internet of Things and privacy protection has been ignored. Inevitably, these users are exposed to a serious risk of privacy breaches in the presence of untrusted service providers and malicious attackers. In this paper, we propose and implement an effective Internet of Things service with differential privacy-preserving to explore collaborative intelligence considering the social interaction of users in social networks. Compared to the outdated approach, our scheme can monitor various parameters of the entire site from the Internet of Things devices, find critical data, and send and deliver the requested service over the Internet in a fast and scalable manner. Additionally, our analysis clearly illustrates that our approach provides guidance for privacy protection in the social Internet of Things. Experiments using real data sets show that our solutions reduce costs, increase flexibility, and provide more accurate and efficient social Internet of Things devices services. We further explore the potential challenges that need to be addressed in this research area.