A Privacy-Preserving System for Enhancing the QoI of Collected Data in a Smart Connected Community

Abstract

The Smart Connected Communities paradigm, which synergistically integrates smart technologies with the surrounding environment, has paved the way for a new generation of applications that provide increasingly intelligent services by leveraging information coming from users, and the IoT. While user collaboration is essential to improve the quality of information (QoI), the interest of providers in data can jeopardize the right to privacy by revealing details that users are not willing to share (e.g., habits, health status). In addition, not all involved users consistently exhibit cooperative behavior, and the presence of attackers often undermines the quality of the collected information. In this paper, we propose a system for aggregating and analyzing user data without ever compromising their privacy, whilst improving QoI. The system uses Privacy Preserving Computation techniques, clustering, and an outlier removal step to improve the quality of information. Utilizing a real-world dataset, we tested our system, demonstrating its resilience in a scenario with potential attackers and its superior performance compared to other state-of-the-art systems.