Differential Privacy in Spatial Task Assignment for Cloud Crowdsourcing

Spatial crowdsourcing platforms enable efficient task assignment based on the geographical locations of workers. However, ensuring the privacy of users’ location data poses a significant challenge. This paper introduces a novel approach to address this challenge by integrating differential privacy principles into the task assignment process. Our proposed framework aims to balance task assignment efficiency with robust privacy protection. We develop an algorithm that considers both task requirements and users’ privacy preferences, optimizing task-worker assignments while preserving the privacy of location data. Experimental evaluation using real-world datasets demonstrates the effectiveness of our approach in enhancing privacy without compromising task assignment efficiency. By providing a principled solution to privacy preservation in cloud-based crowdsourcing platforms, this study contributes to advancing the field and fostering trust among users.