Biometric Authentication using IoT Devices Powered by Deep Learning and Encrypted Verification
International Journal of Computer Technology and Electronics Communication ( · 28.02.2026 · 09 (01)
DOI: 10.15680/ijctece.2026.0901014 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computer Technology and Electronics Communication (, online erschienen am 28.02.2026. Verfasst von S. Chandu und 5 weiteren Autor:innen.
Abstract (Originalsprache)
IoT devices are increasingly targeted by cyber threats, where traditional passwords fail due to phishing and reuse, and raw biometric storage risk irreversible identity loss. This paper proposes an edge-centric biometric authentication system using lightweight deep learning (quantized MobileNetV2 CNN) for feature extraction from fingerprint or face data, cancelable transformations for revocable non-invertible templates, and AES-256 encryption for privacy. On-device processing on Raspberry Pi/ESP32 reduces latency and prevents data exposure. Evaluations on benchmark datasets yield >96% accuracy, EER
Zitieren
APA
Chandu, S., Goutham, T., Badrinath, P., Redy, V. P., Yadav, D. B., & Dharnasi, D. P. (2026). Biometric Authentication using IoT Devices Powered by Deep Learning and Encrypted Verification. International Journal of Computer Technology and Electronics Communication (, 09(01). https://doi.org/10.15680/ijctece.2026.0901014
Vancouver
Chandu S, Goutham T, Badrinath P, Redy VP, Yadav DB, Dharnasi DP. Biometric Authentication using IoT Devices Powered by Deep Learning and Encrypted Verification. International Journal of Computer Technology and Electronics Communication (. 2026;09(01). doi:10.15680/ijctece.2026.0901014
BibTeX
@article{Chandu2026,
author = {Chandu, S. and Goutham, T. and Badrinath, P. and Redy, V. Prashanth and Yadav, D Bhagyaraj and Dharnasi, Dr Prasad},
title = {Biometric Authentication using IoT Devices Powered by Deep Learning and Encrypted Verification},
journal = {International Journal of Computer Technology and Electronics Communication (},
year = {2026},
volume = {09},
number = {01},
doi = {10.15680/ijctece.2026.0901014}
}
EUVIMED