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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Dowling, Byron, Piland, Jacob, Frederick, Eleanor, Sweet, Christopher, Czajka, Adam
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917467468595200
author Dowling, Byron
Piland, Jacob
Frederick, Eleanor
Sweet, Christopher
Czajka, Adam
author_facet Dowling, Byron
Piland, Jacob
Frederick, Eleanor
Sweet, Christopher
Czajka, Adam
contents 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 under-explored. In this paper, we conduct a series of experiments comparing hand annotations, eye tracking heatmaps, segmentation masks, and foundation model 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 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_17859
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VISER: Visually-Informed System for Enhanced Robustness in Open-Set Iris Presentation Attack Detection
Dowling, Byron
Piland, Jacob
Frederick, Eleanor
Sweet, Christopher
Czajka, Adam
Computer Vision and Pattern Recognition
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 under-explored. In this paper, we conduct a series of experiments comparing hand annotations, eye tracking heatmaps, segmentation masks, and foundation model 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 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.
title VISER: Visually-Informed System for Enhanced Robustness in Open-Set Iris Presentation Attack Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.17859