AI-Driven Voter Access and Authentication in a Blockchain-Based Secure Voting System

Abstract

Democratic participation depends on voting; however, conventional voting systems remain vulnerable to voter impersonation, unauthorized entry, repeated voting, and ballot manipulation. This paper proposes an AI-driven voter authentication and access system that combines blockchain technology to strengthen voting security and transparency. Facial recognition is applied to confirm voter identities and permit access only to eligible voters. RetinaFace performs face detection, whereas FaceNet512 produces facial feature embeddings for identity validation. Facial embeddings are compared using Euclidean distance, with FAISS enabling efficient matching of facial features. Ethereum blockchain and Solidity smart contracts store voting records and help prevent duplicate voting. Data integrity is supported through SHA-256 hashing, while Ganache serves as a local blockchain platform for development and testing. The backend is built with Java and Spring Boot, and Web3j connects the application to the Ethereum blockchain. The proposed platform is intended to deliver secure, transparent, and dependable electronic voting. Its performance, however, relies on accurate implementation and additional systematic testing.

Introduction

The AI-Driven Voter Access and Authentication in a Blockchain-Based Secure Voting System aims to develop a secure, transparent, and reliable electronic voting platform by integrating Artificial Intelligence (AI), facial recognition, and blockchain technology. The system is designed to prevent unauthorized access, identity impersonation, and duplicate voting while maintaining the integrity of voting records.

The proposed system uses RetinaFace for face detection and FaceNet512 to extract 512-dimensional facial features. Euclidean distance is used to compare facial embeddings, while FAISS supports efficient facial similarity matching. Once the voter's identity is verified, the system checks their eligibility and voting status before granting access to the voting interface.

The backend is developed using Java and Spring Boot, with Spring Security and JWT for access control. A local server manages voter registration and application data. Ethereum blockchain and Solidity smart contracts are used to record voting transactions and prevent duplicate voting. Web3j enables communication between the backend and blockchain, while Ganache provides a local environment for development and testing. SHA-256 hashing helps maintain the integrity of vote-related data.

The system combines biometric authentication, secure backend processing, and blockchain-based vote recording to improve the reliability and transparency of electronic elections. Overall, the project aims to provide a secure and dependable voting platform that ensures only authorized voters can participate and helps prevent vote manipulation and repeated voting.

Conclusion

VoteSecure AI – AI-Driven Voter Access and Authentication in a Blockchain-Based Secure Voting System is proposed to strengthen the security, accessibility, and transparency of electronic voting through the combined use of artificial intelligence, biometric authentication, and blockchain technology. The system is intended to address key concerns in electronic voting, such as unauthorized access, voter identity validation, duplicate voting, and the preservation of voting-record integrity. The proposed design connects a web frontend built with HTML5, CSS3, and JavaScript to a Java Spring Boot backend. Its biometric verification process uses RetinaFace for face detection and FaceNet512 to create 512-dimensional facial embeddings. Euclidean distance and FAISS are used for facial comparison and similarity searches. Ethereum and Solidity smart contracts form the blockchain portion of the system, supporting the enforcement of voting rules and the recording of transactions. Ganache is used as a local blockchain setting for development and testing, whereas Web3j enables interaction between the Java backend and the blockchain. The proposed workflow also includes SHA-256 hashing to check the integrity of vote-related information. The provided interface screenshots show the structure of the voting portal, including the home page, voter login, voter dashboard, candidate list, and election-results dashboard. These screens indicate how voter details and voting-related outcomes are displayed within the application. Overall, the project presents a modular method for combining AI-supported voter verification with blockchain-based voting processes. To determine whether the system is reliable, privacy-preserving, and appropriate for real-world elections, further implementation validation, security evaluation, and controlled testing are needed.

References

[1] F. Schroff, D. Kalenichenko, and J. Philbin, “FaceNet: A Unified Embedding for Face Recognition and Clustering,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 815–823, 2015. [Online]. Available: https://doi.org/10.1109/CVPR.2015.7298682 [2] J. Deng, J. Guo, E. Ververas, I. Kotsia, and S. Zafeiriou, “RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5203–5212, 2020. [Online]. Available: https://doi.org/10.1109/CVPR42600.2020.00525 [3] M. Douze, A. Guzhva, C. Deng, J. Johnson, G. Szilvasy, P. Mazaré, M. Lomeli, L. Hosseini, and H. Jégou, “The Faiss Library,” arXiv preprint arXiv:2401.08281, 2024. [Online]. Available: https://doi.org/10.48550/arXiv.2401.08281 [4] National Institute of Standards and Technology, “Secure Hash Standard (SHS),” Federal Information Processing Standards Publication 180-4, 2015. [Online]. Available: https://doi.org/10.6028/NIST.FIPS.180-4 [5] V. Buterin, “A Next-Generation Smart Contract and Decentralized Application Platform,” Ethereum Whitepaper, 2014. [Online]. Available: https://ethereum.org/whitepaper/ [6] Ethereum Foundation, “Solidity Documentation.” [Online]. Available: https://docs.soliditylang.org/ [7] OpenCV, “OpenCV Documentation.” [Online]. Available: https://docs.opencv.org/ [8] Spring, “Spring Security Reference Documentation.” [Online]. Available: https://docs.spring.io/spring-security/reference/ [9] National Institute of Standards and Technology, “Digital Identity Guidelines: Authentication and Lifecycle Management,” NIST Special Publication 800-63B. [Online]. Available: https://pages.nist.gov/800-63-3/sp800-63b.html [10] H. Baniata and G. Caluna, “BP-Vot: Blockchain-Based e-Voting Using Smart Contracts, Differential Privacy, and Self-Sovereign Identities,” IEEE Access, vol. 13, pp. 46106–46123, 2025. [Online]. Available: https://doi.org/10.1109/ACCESS.2025.3548404

Copyright

Copyright © 2026 Bindu R, HemaShree K, M S Nishamya, Thanushree H R, Dr. Sreenivasa Murthy V. This 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.