Accès ouvert · CC BY

Enhancing Network Access Control using Multi-Modal Biometric Authentication Framework

Article scientifique 2025 Sciences mathématiques et statistiques Anglais

Résumé

This study presents an innovative multi-modal biometric authentication framework that integrates Deep Learning (DL) techniques with zero-trust architecture principles for enhanced network access control. The framework employs a three-tier fusion strategy (feature-level, score-level, and decision-level) incorporating facial, fingerprint, and iris recognition modalities. The system architecture implements a sophisticated multi-layered approach utilizing the ResNet-50 based Convolutional Neural Network (CNN) architecture for facial recognition, CNN-based minutiae extraction for fingerprint processing, and 2D Gabor wavelets with DL-based feature extraction for iris analysis. The experimental validation using established datasets, namely Labeled Faces in the Wild (LFW), CelebA, FVC2004, NIST SD14, CASIA Iris V4, and UBIRIS v2, demonstrates exceptional performance with 99.47% authentication accuracy, 0.02% False Acceptance Rate (FAR), and 0.15% False Rejection Rate (FRR). The framework resulted in a 68% reduction in fraudulent access attempts. It achieved a mean authentication time of 235 ms (SD=28 ms), representing a 45% improvement over traditional systems. The resource efficiency analysis showed significant reductions in system overhead: 32% in CPU utilization, 28% in memory consumption, and 45% in network bandwidth requirements. The scalability testing confirmed a linear performance scaling up to 100,000 concurrent authentication requests. The statistical test of significance through t-test confirmed the framework's significant improvements over existing solutions (p-value<0.001). This study establishes an effective framework to address network access control challenges across various sectors, particularly in high-security environments requiring robust authentication mechanisms.

Citer ce document

Mohammed, A., Salama, A. A., Shebka, N., & Ismail, A. (2025). Enhancing Network Access Control using Multi-Modal Biometric Authentication Framework. Engineering Technology & Applied Science Research. https://doi.org/10.48084/etasr.9554

Exporter : BibTeX · RIS (Zotero, Mendeley, EndNote)

Accès au document

Texte intégral archivé sur SPHAERO, en accès ouvert : lisible gratuitement en ligne après connexion. Le document reste aussi disponible à sa source. Se connecter

Voir l'article sur le site de la revue

Licence et provenance

Licence : CC BY

Notice moissonnée depuis OpenAlex le 28/09/2026. Le document reste hébergé par sa source.
Voir le document à la source →

Statistiques

Consultations (hors robots) : 8

Téléchargements (hors robots) : 0

Méthode de comptage