Virtual camera detection: Catching video injection attacks in remote biometric systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kurmankhojayev, Daniyar, Shadrikov, Andrei, Gordin, Dmitrii, Shkorin, Mikhail, Gabdullin, Danijar, Kambetbayeva, Aigerim, Kuatov, Kanat
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909957070258176
author Kurmankhojayev, Daniyar
Shadrikov, Andrei
Gordin, Dmitrii
Shkorin, Mikhail
Gabdullin, Danijar
Kambetbayeva, Aigerim
Kuatov, Kanat
author_facet Kurmankhojayev, Daniyar
Shadrikov, Andrei
Gordin, Dmitrii
Shkorin, Mikhail
Gabdullin, Danijar
Kambetbayeva, Aigerim
Kuatov, Kanat
contents Face anti-spoofing (FAS) is a vital component of remote biometric authentication systems based on facial recognition, increasingly used across web-based applications. Among emerging threats, video injection attacks -- facilitated by technologies such as deepfakes and virtual camera software -- pose significant challenges to system integrity. While virtual camera detection (VCD) has shown potential as a countermeasure, existing literature offers limited insight into its practical implementation and evaluation. This study introduces a machine learning-based approach to VCD, with a focus on its design and validation. The model is trained on metadata collected during sessions with authentic users. Empirical results demonstrate its effectiveness in identifying video injection attempts and reducing the risk of malicious users bypassing FAS systems.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10653
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Virtual camera detection: Catching video injection attacks in remote biometric systems
Kurmankhojayev, Daniyar
Shadrikov, Andrei
Gordin, Dmitrii
Shkorin, Mikhail
Gabdullin, Danijar
Kambetbayeva, Aigerim
Kuatov, Kanat
Cryptography and Security
Machine Learning
Face anti-spoofing (FAS) is a vital component of remote biometric authentication systems based on facial recognition, increasingly used across web-based applications. Among emerging threats, video injection attacks -- facilitated by technologies such as deepfakes and virtual camera software -- pose significant challenges to system integrity. While virtual camera detection (VCD) has shown potential as a countermeasure, existing literature offers limited insight into its practical implementation and evaluation. This study introduces a machine learning-based approach to VCD, with a focus on its design and validation. The model is trained on metadata collected during sessions with authentic users. Empirical results demonstrate its effectiveness in identifying video injection attempts and reducing the risk of malicious users bypassing FAS systems.
title Virtual camera detection: Catching video injection attacks in remote biometric systems
topic Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2512.10653