Saved in:
Bibliographic Details
Main Authors: Roux, Quentin Le, Teglia, Yannick, Furon, Teddy, Loubet-Moundi, Philippe, Bourbao, Eric
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.01607
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912832509968384
author Roux, Quentin Le
Teglia, Yannick
Furon, Teddy
Loubet-Moundi, Philippe
Bourbao, Eric
author_facet Roux, Quentin Le
Teglia, Yannick
Furon, Teddy
Loubet-Moundi, Philippe
Bourbao, Eric
contents The widespread deployment of Deep Learning-based Face Recognition Systems raises many security concerns. While prior research has identified backdoor vulnerabilities on isolated components, Backdoor Attacks on real-world, unconstrained pipelines remain underexplored. This SoK paper presents the first comprehensive system-level analysis and measurement of the impact of Backdoor Attacks on fully-fledged Face Recognition Systems. We combine the existing Supervised Learning backdoor literature targeting face detectors, face antispoofing, and face feature extractors to demonstrate a system-level vulnerability. By analyzing 20 pipeline configurations and 15 attack scenarios in a holistic manner, we reveal that an attacker only needs a single backdoored model to compromise an entire Face Recognition System. Finally, we discuss the impact of such attacks and propose best practices and countermeasures for stakeholders.
format Preprint
id arxiv_https___arxiv_org_abs_2507_01607
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SoK: On the Survivability of Backdoor Attacks on Unconstrained Face Recognition Systems
Roux, Quentin Le
Teglia, Yannick
Furon, Teddy
Loubet-Moundi, Philippe
Bourbao, Eric
Computer Vision and Pattern Recognition
Artificial Intelligence
Cryptography and Security
Machine Learning
The widespread deployment of Deep Learning-based Face Recognition Systems raises many security concerns. While prior research has identified backdoor vulnerabilities on isolated components, Backdoor Attacks on real-world, unconstrained pipelines remain underexplored. This SoK paper presents the first comprehensive system-level analysis and measurement of the impact of Backdoor Attacks on fully-fledged Face Recognition Systems. We combine the existing Supervised Learning backdoor literature targeting face detectors, face antispoofing, and face feature extractors to demonstrate a system-level vulnerability. By analyzing 20 pipeline configurations and 15 attack scenarios in a holistic manner, we reveal that an attacker only needs a single backdoored model to compromise an entire Face Recognition System. Finally, we discuss the impact of such attacks and propose best practices and countermeasures for stakeholders.
title SoK: On the Survivability of Backdoor Attacks on Unconstrained Face Recognition Systems
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2507.01607