Research
VISER: Visually-Informed System for Enhanced Robustness in Iris Presentation Attack Detection
arXiv:2603.17859v3 Announce Type: replace Abstract: Human perceptual priors have shown promise in saliency-guided deep learning training, particularly in the domain of iris presentation attack detecti
arXiv:2603.17859v3 Announce Type: replace 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 raising generalization to unknown attack classes in 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 unknown attack type classification for iris PAD. Results 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.
Related
- Beyond Perceptual Distance: Discrepancy Assessment on Deep Representation for Out-of-Distribution Detection with Diffusion Model
- Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures
- A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP
Source: arXiv cs.CV | 2026-09-09