An Efficient and Privacy-Preserving $k$-NN Query Scheme for eHealthcare Data

Abstract

As eHealthcare data is very sensitive yet cloud servers are not fully trustable today, many security, privacy and efficiency challenges will arise when cloud meets eHealthcare data. In this paper, aiming at addressing the privacy and efficiency challenges, we present an efficient and privacy-preserving $k$ Nearest Neighbour ( $k$ -NN) query scheme for encrypted eHealthcare data in cloud. The proposed scheme is characterized by integrating kd-tree and homomorphic encryption techniques for efficient storing encrypted data in cloud and privacy-preserving $k$ -NN query over encrypted data. Detailed security analysis shows that our proposed scheme is really privacy preserving under our security model. In addition, performance evaluation also indicates that our proposed scheme is efficient in terms of computational complexity.