Enabling Efficient and Privacy-Preserving Health Query Over Outsourced Cloud

With the pervasiveness of Body Sensor Network (BSN) and cloud computing, online health query service has attracted considerable attention and become a promising approach to improve our quality of healthcare service. However, it still faces many challenges on privacy of users' sensitive personal information, confidentiality of health service provider's diagnosis model, accuracy of the diagnosis result, and efficiency of the query result. In this paper, we propose an efficient and privacy-preserving health query scheme over outsourced cloud named HeOC. In the HeOC scheme, the authenticated users can send the encrypted physiological data to the cloud and query the specific disease level accurately on the encrypted medical data stored in the cloud. To reduce the query latency, we fist design a sensor anomaly detection technique to find the high risk disease according to the user's sensor information. Then, with the oblivious pseudorandom function protocol, the user queries the diagnosis result accurately. Detailed security analysis shows that the HeOC scheme can achieve the diagnosis without disclosing the privacy of the user's health information and confidentiality of the health service provider's diagnosis model. In addition, the extensive experiments with an android app and two python programs demonstrate its efficiency in computations and communications.