Truthful Incentives for Privacy Tradeo: Mechanisms for Data Gathering in Community Sensing

Community sensing, fusing information from populations of privately-held sensors, presents a great opportunity to create ecient and cost-eective sensing applications. Yet, reasonable privacy concerns often limit the access to such data streams. How should systems valuate and negotiate access to private information, for example in return for monetary incentives? How should they optimally choose the participants from a large population of strategic users with privacy concerns, and compensate them for information shared? In this paper, we address these questions and present a novel mechanism, SeqTGreedy, for budgeted recruitment of participants in community sensing. By exploiting a link between privacy tradeos in community sensing and adaptive submodularity, we prove that SeqTGreedy is budget feasible, incentive compatible (truthful) for participants and achieves near-optimal utility for a large class of sensing applications. We demonstrate the eectiveness of our approach in a case study of air quality monitoring, using data collected from the Mechanical Turk platform. Compared to the state of the art, our approach achieves up to 10% increase in acquired utility (for a given budget) and up to 30% reduction in cost (to achieve a desired level of utility).