MASK: Efficient and privacy-preserving m-tree based biometric identification over cloud

In recent years, the extensive application of biometric identification has been witnessed in various fields, such as airport service, criminal investigation, counter-terrorism and so on. Due to the sensitivity of the biometric data, people’s concern over the leakage of their biometric data is a critical obstacle to hinder the future adoption of biometric identification applications. To address this problem, many schemes focusing on the privacy protection during biometric identification process have been proposed. However, identifying an individual in a huge database still faces many challenges while considering privacy protection and efficiency at the same time. In this paper, an efficient and privacy-preserving cloud based biometric identification scheme (named MASK) is proposed based on the M-tree data structure and symmetric homomorphic encryption (SHE) scheme. With MASK, the privacy of the user’s identification request and service provider’s dataset is guaranteed, while the computational cost of the cloud servers in searching the biometric dataset is significantly reduced. Besides, the accuracy of the identification service is not lost. Detailed security analysis shows that MASK can resist various known security threats. In addition, MASK is implemented and evaluated with a synthetic dataset and a real face dataset, and extensive simulation results demonstrate that MASK is efficient in terms of computational and communication costs.