Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

VISER: Visually-Informed System for Enhanced Robustness in Open-Set Iris Presentation Attack Detection

Byron Dowling, Eleanor Frederick, Jacob Piland, Adam Czajka

Abstract

Human perceptual priors have shown promise in saliency-guided deep learning training, particularly in the domain of iris presentation attack detection (PAD). Common saliency approaches include hand annotations obtained via mouse clicks and eye gaze heatmaps derived from eye tracking data. However, the most effective form of human saliency for open-set iris PAD remains underexplored. In this paper, we conduct a series of experiments comparing hand annotations, eye tracking heatmaps, segmentation masks, and DINOv2 embeddings to a state-of-the-art deep learning-based baseline on the task of open-set iris PAD. Results for open-set PAD in a leave-one-attack-type out paradigm indicate that denoised eye tracking heatmaps show the best generalization improvement over cross entropy in terms of Area Under the ROC curve (AUROC) and Attack Presentation Classification Error Rate (APCER) at Bona Fide Presentation Classification Error Rate (BPCER) of 1%. Along with this paper, we offer trained models, code, and saliency maps for reproducibility and to facilitate follow-up research efforts.

VISER: Visually-Informed System for Enhanced Robustness in Open-Set Iris Presentation Attack Detection

Abstract

Human perceptual priors have shown promise in saliency-guided deep learning training, particularly in the domain of iris presentation attack detection (PAD). Common saliency approaches include hand annotations obtained via mouse clicks and eye gaze heatmaps derived from eye tracking data. However, the most effective form of human saliency for open-set iris PAD remains underexplored. In this paper, we conduct a series of experiments comparing hand annotations, eye tracking heatmaps, segmentation masks, and DINOv2 embeddings to a state-of-the-art deep learning-based baseline on the task of open-set iris PAD. Results for open-set PAD in a leave-one-attack-type out paradigm indicate that denoised eye tracking heatmaps show the best generalization improvement over cross entropy in terms of Area Under the ROC curve (AUROC) and Attack Presentation Classification Error Rate (APCER) at Bona Fide Presentation Classification Error Rate (BPCER) of 1%. Along with this paper, we offer trained models, code, and saliency maps for reproducibility and to facilitate follow-up research efforts.
Paper Structure (20 sections, 3 figures, 2 tables)

This paper contains 20 sections, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Detection of Biometric Presentation Attacks
  4. Human Saliency-Guided Training
  5. Visual vs Motor Saliency
  6. Experimental Design
  7. Metrics
  8. Dataset Sources
  9. Saliency Methods
  10. Segmentation Masks
  11. Hand Annotations
  12. Eye Tracking
  13. No Saliency: Foundation Model Baseline
  14. Results
  15. Answering RQ1: Does the use of eye tracking saliency in saliency-guided training generalize better to unseen data than other saliency types?
  16. ...and 5 more sections

Figures (3)

  • Figure 1: Experimental pipeline and contributions. A deep learning iris presentation attack detection model trained without saliency guidance serves as the baseline. We evaluate multiple saliency modalities through saliency-guided training, and further assess foundation model-sourced embeddings using logistic regression, linear-SVM, and RBF-SVM classifiers. Performance is reported in terms of Area Under the ROC curve (AUROC) and Attack Presentation Classification Rate (APCER) at 1% Bonafide Presentation Classification Rate (BPCER), expressed as relative improvement over the baseline trained traditionally.
  • Figure 2: Example of applying HDBSCAN to de-noise the eye tracking data. Clusters made up of valid fixations are distinguished by color and larger marks denote longer fixations, not fixation area. Black crosses indicate fixations marked as noise excluded from the final saliency map.
  • Figure 3: Sample salience types captured for the same iris image.