Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{184992,
        author = {Nisarga .P and Nethravathy V},
        title = {Secure Biometric Authentication for Banking Systems: Integrating Iris Recognition and Password Verification},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {4},
        pages = {4317-4323},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=184992},
        abstract = {The rapid growth of digital banking necessitates robust authentication to counter escalating cyber threats. This paper presents a dual-factor authentication system integrating iris recognition, powered by a Vision Transformer (ViT), with bcrypt-based password verification for secure banking access. Iris images are captured via webcam, preprocessed with CLAHE, and augmented with brightness adjustments, rotations, and noise to ensure robustness. The system generates 256-dimensional embeddings, compared using cosine similarity, and supports transactions via a Tkinter dashboard, with balances secured by Paillier homomorphic encryption. Evaluation on enrolment embeddings yields 90.6% accuracy, 0.917 ROC AUC. By reviewing 20 journal papers (2021–2025), we position our work as a practical, high-security solution for banking. The system balances usability and efficiency, suitable for resource constrained environments.},
        keywords = {Iris recognition, Biometric authentication, Vision Transformer, Multi-factor authentication, Banking dashboard, Homomorphic encryption, Data augmentation, Cosine similarity},
        month = {September},
        }