Consortium Blockchain-Based SIFT: Outsourcing Encrypted Feature Extraction in the D2D Network

Privacy-preserving outsourcing algorithms for feature extraction not only reduce users' storage and computation overhead but also preserve the image privacy. However, the existing schemes still suffer from deficiencies induced by security, applications, efficiency and storage. To solve the problems, we implement a consortium chain-based outsourcing feature extraction scheme over encrypted images by using the smart contract, distributed autonomous corporation (DAC), sharding technique, and device to device (D2D) communication, which is secure, widely applied, highly efficient, and has less storage overhead. First, the effectiveness, security, and performance of our scheme are analyzed. Then, the efficiency and storage overhead of our scheme are presented by conducting experimental results.

Abstract licence: CC BY-NC-ND

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.