mlsanityData to 7 Oct 2026

Are Explainability Tools Gender Biased? A Case Study on Face Presentation Attack Detection

arXiv 2304.13419 ↗First posted 26 Apr 2023cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Face recognition (FR) systems continue to spread in our daily lives with an increasing demand for higher explainability and interpretability of FR systems that are mainly based on deep learning. While bias across demographic groups in FR systems has already been studied, the bias of explainability tools has not yet been investigated. As such tools aim at steering further development and enabling a better understanding of computer vision problems, the possible existence of bias in their outcome can lead to a chain of biased decisions. In this paper, we explore the existence of bias in the outcome of explainability tools by investigating the use case of face presentation attack detection. By utilizing two different explainability tools on models with different levels of bias, we investigate the bias in the outcome of such tools. Our study shows that these tools show clear signs of gender bias in the quality of their explanations.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 20 of its 25 references that are in the map. First posted on arXiv 26 Apr 2023.

Builds on

20 of 25 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  4. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
  5. 2021MagFace: A Universal Representation for Face Recognition and Quality Assessmentcited by 332
  6. 2021ElasticFace: Elastic Margin Loss for Deep Face Recognitioncited by 143
  7. 2020CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotationscited by 109
  8. 2019Regularized Fine-grained Meta Face Anti-spoofingcited by 86
  9. 2021A Comprehensive Study on Face Recognition Biases Beyond Demographicscited by 86
  10. 2020Revisiting Pixel-Wise Supervision for Face Anti-Spoofingcited by 45
  11. 2020Fairness in Biometrics: a figure of merit to assess biometric verification systemscited by 41
  12. 2020Face Quality Estimation and Its Correlation to Demographic and Non-Demographic Bias in Face Recognitioncited by 31
8 more
  1. 2021Learnable Multi-level Frequency Decomposition and Hierarchical Attention Mechanism for Generalized Face Presentation Attack Detectioncited by 18
  2. 2023SynthASpoof: Developing Face Presentation Attack Detection Based on Privacy-friendly Synthetic Datacited by 17
  3. 2021Pixel-Level Face Image Quality Assessment for Explainable Face Recognitioncited by 14
  4. 2022Fairness in Face Presentation Attack Detectioncited by 13
  5. 2022Causality-Inspired Taxonomy for Explainable Artificial Intelligencecited by 9
  6. 2021Myope Models -- Are face presentation attack detection models short-sighted?cited by 6
  7. 2022Assessing Bias in Face Image Quality Assessmentcited by 5
  8. 2021Explaining Face Presentation Attack Detection Using Natural Languagecited by 2

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 3; 2025: 1.

6 papers.

  1. 2023Bias and Diversity in Synthetic-based Face Recognitioncited by 11
  2. 2024Model Compression Techniques in Biometrics Applications: A Surveycited by 4
  3. 2024Fairness Under Cover: Evaluating the Impact of Occlusions on Demographic Bias in Facial Recognitioncited by 3
  4. 2024Gender Representation and Bias in Indian Civil Service Mock Interviewscited by 2
  5. 2023Explanation-based Training with Differentiable Insertion/Deletion Metric-aware Regularizerscited by 0
  6. 2025Explainable Face Presentation Attack Detection via Ensemble-CAMcited by 0