Publication Type

Journal Article

Version

submittedVersion

Publication Date

9-2025

Abstract

Face recognition is a widely used authentication technology in practice, where robustness is required. It is thus essential to have an efficient and easy-to-use method for evaluating the robustness of (possibly third-party) trained face recognition systems. Existing approaches to evaluating the robustness of face recognition systems are either based on empirical evaluation (e.g., measuring attacking success rate using state-of-the-art attacking methods) or formal analysis (e.g., measuring the Lipschitz constant). While the former demands significant user efforts and expertise, the latter is extremely time-consuming. In pursuit of a comprehensive, efficient, easy-to-use, and scalable estimation of the robustness of face recognition systems, we take an old-school alternative approach and introduce RobFace, i.e., evaluation using an optimized test suite. It contains transferable adversarial face images that are designed to comprehensively evaluate a face recognition system’s robustness along a variety of dimensions. RobFace is system-agnostic and still consistent with system-specific empirical evaluation or formal analysis. We support this claim through extensive experimental results with various perturbations on multiple face recognition systems. To our knowledge, RobFace is the first system-agnostic robustness estimation test suite.

Keywords

Face recognition, robustness

Discipline

Graphics and Human Computer Interfaces | Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

IEEE Transactions on Reliability

Volume

74

Issue

3

First Page

3615

Last Page

3628

ISSN

0018-9529

Identifier

10.1109/TR.2025.3554575

Publisher

Institute of Electrical and Electronics Engineers

Copyright Owner and License

Authors-NC-SA

Additional URL

https://doi.org/10.1109/TR.2025.3554575

Download

Share

COinS