TRUSTVOTE: SECURE AND TRANSPARENT VOTING SYSTEM LEVERAGING AI-ENABLED IRIS BIOMETRICS

Abstract

Ensuring the integrity, transparency, and security of voting systems remains a critical challenge in the digital era. Traditional electronic voting systems are vulnerable to identity fraud, unauthorized access, and data manipulation, compromising public trust in electoral processes. To address these challenges, this research introduces TrustVote, a machine learning-based iris recognition framework designed to enhance the reliability and security of modern voting systems. The proposed model leverages AI-enabled biometric authentication using iris patterns, which provide highly unique and stable identifiers for individuals, making them ideal for secure voter verification. The system employs advanced feature extraction and classification algorithms such as convolutional neural networks (CNNs) to accurately recognize and authenticate voters based on their iris images. By integrating machine learning with cryptographic protocols, TrustVote ensures end-to-end security— protecting biometric data, preventing duplication, and eliminating false identities. Furthermore, the system incorporates a transparent audit mechanism that records and verifies each vote securely, thereby enhancing accountability and trustworthiness. Experimental results demonstrate that TrustVote achieves high accuracy in voter authentication, significantly reducing the chances of impersonation and fraudulent voting. The proposed framework not only strengthens election security but also promotes efficiency, scalability, and accessibility in electronic voting environments. This study establishes TrustVote as a step toward building intelligent, transparent, and tamper-proof voting systems empowered by artificial intelligence and biometric innovation.