SoK: On the Survivability of Backdoor Attacks on Unconstrained Face Recognition Systems

TL;DR

This paper provides a comprehensive analysis of backdoor attacks on real-world face recognition systems, revealing their potential to compromise entire pipelines and offering insights into mitigation strategies.

Contribution

It is the first to systematically evaluate backdoor vulnerabilities at the system level in unconstrained face recognition pipelines, combining multiple attack scenarios and configurations.

Findings

A single backdoored model can compromise the entire face recognition system.

Analysis of 20 pipeline configurations and 15 attack scenarios.

Discussion of best practices and countermeasures for stakeholders.

Abstract

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.