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{195200,
        author = {D Manichakradeep and Matru Dhanavath and U Jayanth and G Manideep and B Dileep},
        title = {Iris Detection for Secure Voting System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {7005-7008},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195200},
        abstract = {When democracy comes to mind, the security of each and every single vote strikes the mind. Traditional electronic voting systems —and even modern systems that depend on PINs or fingerprints—still have weak spots. Passwords can easily be shared, and fingerprint scanners can be fooled by personification attacks (like fake silicone prints) or fail to read worn-out fingers. In this project, we decided to tackle this problem by using human iris. The iris is unique to every person and practically impossible to fake. To make this idea a reality, we built complete, standalone voting framework. We utilized Convolutional Neural Networks (CNNs) to scan and process a voter's iris in real-time. Instead of saving this sensitive biometric info out in the open, we encrypted everything using strong AES-256 encryption before storing it in a local SQLite database. Furthermore, we built a tamper-proof audit log using SHA-256 hash chaining, meaning every single action is recorded. Nobody, not even an administrator, can secretly change or delete a vote without breaking the cryptographic chain. Our testing showed that the system is incredibly accurate and fast, proving that next-generation voting machines can be highly reliable and extremely protective of user privacy.},
        keywords = {},
        month = {March},
        }