Differentially Private Double Auction with Reliability-Aware in Mobile Crowd Sensing

With the unprecedented proliferation of mobile devices, Mobile Crowd Sensing (MCS) emerges as a promising computing paradigm which utilizes sensor-embedded smart devices to collect sensory data. Recently, a number of privacy-preserving auction-based incentive mechanisms have been proposed. However, none of them guarantees the quality of sensing data in double-side auction scenarios. In this paper, we propose a Differentially Private Double Auction With Reliability-Aware in Mobile Crowd Sensing (DPDR). Specifically, we design the incentive mechanism by employing the exponential mechanism in double-side auction to select the clearing price tuple. Moreover, to collect precise sensory data, we heuristically choose more reliable workers as candidates for each clearing price tuple. We further improve the social welfare of the mechanism by designing the utility function with less sensitivity, or adopting a more practical pricing strategy. Through theoretical analysis, we demonstrate that our mechanisms can guarantee both differential privacy and economic properties, including individual rationality, budget balance, approximate truthfulness and approximate maximal social welfare. Extensive experimental results show that the improved mechanisms can achieve better performance than DPDR in term of social welfare, and all proposed mechanisms can produce high-quality data.