Open Access

ARTICLE

A Quantum-Enhanced Biometric Fusion Network for Cybersecurity Using Face and Voice Recognition

Abrar M. Alajlan^1,*, Abdul Razaque²

1 Self-Development Skills Department, Commonrst Year Deanship, King Saud University, Riyadh, 11362, Saudi Arabia
2 Department of Cybersecurity, International Information Technology University, Almaty, 050000, Kazakhstan

* Corresponding Author: Abrar M. Alajlan. Email:

Computer Modeling in Engineering & Sciences 2025, 145(1), 919-946. https://doi.org/10.32604/cmes.2025.071996

Received 17 August 2025; Accepted 19 September 2025; Issue published 30 October 2025

Abstract

Biometric authentication provides a reliable, user-specific approach for identity verification, significantly enhancing access control and security against unauthorized intrusions in cybersecurity. Unimodal biometric systems that rely on either face or voice recognition encounter several challenges, including inconsistent data quality, environmental noise, and susceptibility to spoofing attacks. To address these limitations, this research introduces a robust multi-modal biometric recognition framework, namely Quantum-Enhanced Biometric Fusion Network. The proposed model strengthens security and boosts recognition accuracy through the fusion of facial and voice features. Furthermore, the model employs advanced pre-processing techniques to generate high-quality facial images and voice recordings, enabling more efficient face and voice recognition. Augmentation techniques are deployed to enhance model performance by enriching the training dataset with diverse and representative samples. The local features are extracted using advanced neural methods, while the voice features are extracted using a Pyramid-1D Wavelet Convolutional Bidirectional Network, which effectively captures speech dynamics. The Quantum Residual Network encodes facial features into quantum states, enabling powerful quantum-enhanced representations. These normalized feature sets are fused using an early fusion strategy that preserves complementary spatial-temporal characteristics. The experimental validation is conducted using a biometric audio and video dataset, with comprehensive evaluations including ablation and statistical analyses. The experimental analyses ensure that the proposed model attains superior performance, outperforming existing biometric methods with an average accuracy of 98.99%. The proposed model improves recognition robustness, making it an efficient multimodal solution for cybersecurity applications.

---

Keywords

---