Race Bias Analysis of Bona Fide Errors in Face Anti-spoofing

Abduh, Latifah; Ivrissimtzis, Ioannis

Abstract

The study of bias in Machine Learning is receiving a lot of attention in recent years, however, few only papers deal explicitly with the problem of race bias in face anti-spoofing. In this paper, we present a systematic study of race bias in face anti-spoofing with three key features: we focus on the classifier’s bona fide errors, where the most significant ethical and legal issues lie; we analyse both the scalar responses of the classifier and its final binary outcomes; the threshold determining the operating point of the classifier is treated as a variable. We apply the proposed bias analysis framework on a VQ-VAE-based face anti-spoofing algorithm. Our main conclusion is that race bias should not necessarily be attributed to different mean values of the response distributions over the various demographics. Instead, it can be better understood as the combined effect of several possible characteristics of these distributions: different means; different variances; bimodal behaviour; the existence of outliers.

Citation

Abduh, L., & Ivrissimtzis, I. (2023). Race Bias Analysis of Bona Fide Errors in Face Anti-spoofing. In CAIP 2023: Computer Analysis of Images and Patterns (23-32). https://doi.org/10.1007/978-3-031-44240-7_3

• Presentation Conference Type: Conference Paper (Published)
• Conference Name: CAIP 2023: The 20th International Conference on Computer Analysis of Images and Patterns
• Start Date: Sep 25, 2023
• End Date: Sep 28, 2023
• Acceptance Date: Jun 30, 2023
• Online Publication Date: Sep 20, 2023
• Publication Date: 2023
• Deposit Date: Aug 23, 2023
• Publicly Available Date: Sep 21, 2024
• Publisher: Springer
• Volume: 14185
• Pages: 23-32
• Series Title: Lecture Notes in Computer Science
• Series ISSN: 0302-9743
• Book Title: CAIP 2023: Computer Analysis of Images and Patterns
• ISBN: 9783031442391
• DOI: https://doi.org/10.1007/978-3-031-44240-7_3
• Public URL: https://durham-repository.worktribe.com/output/1723511
• Publisher URL: https://link.springer.com/conference/caip