SensIR: Towards privacy-sensitive image retrieval in the cloud

Abstract

With the advance in content-based image retrieval and the popularity of Data-as-a-Service, enterprises can outsource their image retrieval systems on cloud platforms to reduce heavy storage, computation, and communication burdens. However, this brings many privacy problems. Although several privacy-preserving image retrieval schemes have been proposed to protect users’ privacy, they have two major drawbacks: i) the outsourced images are fully encrypted and thus cannot be used for other applications, which makes them impractical; ii) they mainly focus on traditional image retrieval systems and do not use new techniques such as convolutional neural network (CNN) to improve the accuracy. To address the above problems, we propose a novel privacy-sensitive image retrieval scheme, named SensIR, to search for similar images from an outsourced image database. In particular, we propose a privacy region detection, PRDet, to prevent private regions of images from exposing. We also propose a partial CNN (PCNN) to reduce the impact of the encrypted pseudorandom pixels. Further, we use similarity-preserving hash encoding and propose a systematic methodology to improve the accuracy of PCNN-based image retrieval when the privacy regions are large. Extensive experiments are conducted to illustrate the efficiency of privacy protection and the superior of the proposed scheme.