In EDS ansehen

DETECTION OF PRINTED FALSE ATTACKS USING NEURAL NETWORKS

Gespeichert in:

Bibliographische Detailangaben
Titel:	DETECTION OF PRINTED FALSE ATTACKS USING NEURAL NETWORKS
Autoren:	Bakhtiyor Abdukadirov
Verlagsinformationen:	Zenodo, 2025.
Publikationsjahr:	2025
Schlagwörter:	classification evaluation metrics, local binary pattern, biometric system, recurrent network, convolutional neural networks, support vector machine, false alarm attack
Beschreibung:	This article discusses a method for detecting false positives against a biometric facial recognition system based on deep convolutional neural networks. The proposed method is designed to detect printed false positives and is tested on open databases of real and fake faces, and the results are analyzed. The types of false positive attacks launched against a biometric system based on existing faces are analyzed.
Publikationsart:	Article
Sprache:	English
DOI:	10.5281/zenodo.17258687
DOI:	10.5281/zenodo.17258688
Rights:	CC BY
Dokumentencode:	edsair.doi.dedup.....c36be9c412bbaecf3616850dfd6efc31
Datenbank:	OpenAIRE

Beschreibung
Abstract:	This article discusses a method for detecting false positives against a biometric facial recognition system based on deep convolutional neural networks. The proposed method is designed to detect printed false positives and is tested on open databases of real and fake faces, and the results are analyzed. The types of false positive attacks launched against a biometric system based on existing faces are analyzed.
DOI:	10.5281/zenodo.17258687