Privacy-preserving iris authentication using fully homomorphic encryption

Abstract

Rapid advancement in technology has led to the use of biometric authentication in every field. In particular, from the past few years, iris recognition systems has gained overwhelming advancement over other biometric traits due to its stability and uniqueness. Directly storing the templates into a centralized server leads to privacy concerns. Many state-of-the-art iris authentication systems based on cancelable biometrics and bio-cryptosystems have been introduced to provide security for the iris templates. However, these works suffer from accuracy loss relative to unprotected systems, or they require auxiliary data (AD), which compromise the privacy of the templates and security of the system. To address this, we propose a novel privacy-preserving iris authentication using fully homomorphic encryption which ensures the confidentiality of the templates and restricts the leakage of data from the templates. Our method improves the recognition accuracy by generating rotation invariant iris codes and reduces the computational time by using the batching scheme. Our approach satisfies all the requirements specified in the ISO/IEC 24745 standard. The proposed method has experimented on four benchmark publicly available iris databases which illustrate that our method can be practically achievable with no loss in the accuracy and preserve the privacy of the iris templates. Our method encrypts and computes the Hamming distance of 2560-dimensional iris features in about 0.0185 seconds only with an equal error rate value of 0.19% for CASIA-V 1.0 database.