Advanced Iris Recognition Framework using EfficientNet And Fully Homomorphic Encryption with Bloom Filters

Iris recognition systems have emerged as a pivotal biometric technology, offering high reliability for secure Authentication System. In this study, we emphasize the indispensable role of iris recognition within authentication frameworks, particularly in response to global health emer-gencies such as the COVID-19 pandemic, which underscored the need for contactless and health-conscious authentication solutions. We propose an advanced secure iris recognition framework that leverages a convolutional neural network (CNN) based on the EfficientNetB7 architecture for robust feature extraction. To ensure enhanced security, the extracted features are encrypted using Fully Homomorphic Encryption (FHE) and organized within a Bloom Filter (BF), thereby satisfying stringent security and privacy requirements. The effectiveness of the proposed system is validated on two benchmark datasets: CASIA-Iris-Syn and IITD_V1. Our approach achieves outstanding results, attaining an accuracy of 0.9998 with an Equal Error Rate (EER) of 0.001 on CASIA-Iris-Syn, and an accuracy of 0.9898 with an EER of 0.024 on IITD_V1. Comparative analysis against existing verification systems demonstrates that the proposed framework not only achieves superior accuracy and security but also addresses the increasing demand for resilient and privacy-preserving biometric authentication systems.