An Efficient and Privacy-Preserving Biometric Identification Scheme in Cloud Computing
The main aim of this project is to propose a novel privacy-preserving biometric identification scheme in the cloud computing using multimodal application.
In a biometric identiﬁcation system, the database owner such as the FBI who is responsible to manage the national fingerprints database, may desire to outsource the enormous biometric data to the cloud server to get rid of the expensive storage and computation costs. However, to preserve the privacy of biometric data, the biometric data has to be encrypted before outsourcing. Whenever a FBI’s partner wants to authenticate an individual’s identity, he turns to the FBI and generates an identiﬁcation query by using the individual’s biometric traits (e.g., fingerprints, irises, voice patterns, facial patterns etc.). The FBI encrypts the query and submits it to the cloud to find the close match. Thus, the challenging problem is how to design a protocol which enables efficient and privacy preserving biometric identiﬁcation in the cloud computing. Most of them mainly concentrate on privacy preservation but ignore the efficiency, such as the schemes based on homomorphic encryption and oblivious transfer.
In this project, we propose an efficient and privacy-preserving bio-metric identification outsourcing scheme. In order to overcome the computational cost and storage expenses our system is proposed. Specifically, the biometric to execute a biometric identification, the database owner encrypts the query data and submits it to the cloud. The cloud performs identification operations over the encrypted database and returns the result to the database owner. A thorough security analysis indicates that the proposed scheme is secure even if attackers can forge identification requests and collude with the cloud. Compared with previous protocols, experimental results show that the proposed scheme achieves a better performance in both preparation and identification procedures.