Authors : Olga Volobuyeva

Volume/Issue : Volume 10 - 2025, Issue 12 - December

Google Scholar : https://tinyurl.com/3mem6ayx

Scribd : https://tinyurl.com/37wka55e

DOI : https://doi.org/10.38124/ijisrt/25dec1561

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Biometric authentication has evolved substantially in recent years as security systems move away from single- modality physiological identifiers toward architectures that incorporate dynamic behavioral indicators. This transition is driven by limitations inherent in static biometric traits and by increasing adversarial sophistication in spoofing techniques capable of imitating fingerprints, facial structures or iris patterns with high fidelity. Research in 2025 places significant emphasis on multi-modal fusion models that integrate heterogeneous biometric signals into unified trust-evaluation frameworks. Behavioral biometrics, once considered secondary indicators, now play a central role in adaptive authentication systems because they offer temporal expressiveness and resistance to replication. This article examines current biometric security trends with a particular focus on fusion architectures, continuous identity verification and behavioral modeling.

Keywords : Biometric Authentication, Behavioral Biometrics, Fusion Models, Continuous Identity Verification, Adaptive Identity Modeling.

References :

1. Ahmed, A., & Traore, I. (2017). A new biometric authentication technology based on mouse dynamics. IEEE Transactions on Dependable and Secure Computing, 4(3), 165–179.
2. Dashevskyi, A. (2025). Intelligent authentication based on user behavior and biometrics. International Scientific Journal “Internauka”. https://doi.org/10.25313/2520-2057-2025-8-11279
3. Dashevskyi, A. (2025). Multi-level biometric authentication system with dynamic behavioral analysis (U.S. Provisional Patent Application No. 63/798,769). United States Patent and Trademark Office.
4. Dashevskyi, A. (2025). Искусственный интеллект в кибербезопасности: адаптивные подходы. Lambert Academic Publishing. ISBN 978-620-84529-40.Gupta, P., & Mahajan, A. (2022). Statistical models of user behavior in continuous authentication. International Journal of Creative Research, 10, 2320–2882.
5. Kalla, D., & Chandrasekaran, A. (2023). Biometric authentication improvements in AI-driven security environments. International Journal of Computer Applications, 185(11), 1–11.
6. Mughayed, A., Al-Zu’bi, S., & Hnaif, A. (2022). Deep learning in behavioral biometric authentication. Cluster Computing, 25, 3819–3828.
7. Rizvi, V. (2023). AI and identity scoring in modern authentication frameworks. International Journal of Advanced Engineering Research and Science, 10(5).
8. Safi, A., & Singh, S. (2023). Multi-modal approaches to biometric threat mitigation. King Saud University Journal of Computer and Information Sciences.
9. Salloum, S., Gaber, T., Vadera, S., & Shaalan, K. (2022). Behavioral biometrics and NLP-integrated authentication pipelines. IEEE Access, 10, 65703–65727.
10. Smith, N., Kuraku, S., & Samaa, F. (2023). Multi-modal identity frameworks based on adaptive learning. International Journal of Data and Knowledge Processing, 13(3).