SPRIDE: Scalable and private continual geo-distance evaluation for precision agriculture

Precision agriculture relies on real-time data gathering and analysis to maximize yield, minimize environmental impact and reduce cost, which has been envisioned as a new paradigm to revolutionize modern agriculture. However, the collection of farming data, especially geospatial data, raises concerns about potential privacy leakage. In this paper, we propose a novel scalable and private continual geo-distance evaluation system, called SPRIDE, to allow application servers to provide geographic based services by computing the distances among sensors and farms privately and continuously. The servers determine the distances without learning any additional information about their locations. The key idea of SPRIDE is to perform efficient distance evaluations on encrypted locations over a sphere by leveraging a homomorphic cryptosystem. To scale for a large user base, we propose novel and practical performance enhancements based on data segmentation and distance prediction techniques for reducing computation/communication costs. Through extensive experiments on a real world mobile trace dataset, we show SPRIDE achieves real-time private distance evaluation on a large network of farms, attaining at least 17 times runtime performance improvement over existing methods. We further show SPRIDE can run on resource-constrained mobile devices with low overhead.