Privacy-preserving Multi-Instance Iris Authentication using Homomorphic Encryption

The usage of a biometric authentication system (BAS) for reliable automatic human recognition has increased exponentially in recent years over traditional authentication systems. Since the biometric traits are irrevocable, two important issues such as security & privacy still need to be addressed in BAS. Researchers explore homomorphic encryption (HE) to propose several privacy-preserving BAS. These methods are unable to retain the trade-off between accuracy, security, & speed. To address this, we propose a privacy-preserving multi-instance iris authentication system using Paillier HE (PPMIAP). Modified local random projection is applied on the fused iris template to generate the reduced template. Later, Paillier HE is applied on the reduced template to create the protected template. The efficiency of PPMIAP is verified by experimenting with it on IITD, SDUMLA-HMT, and CASIA iris databases. PPMIAP gratifies the irreversibility, diversity, and revocability properties. PPMIAP also obtains fair performance when compared to the existing methods.