VISER: Visually-Informed System for Enhanced Robustness in Open-Set Iris Presentation Attack Detection
This work addresses the challenge of enhancing robustness in biometric security systems, specifically for iris presentation attack detection, but is incremental as it compares existing saliency methods without introducing a new paradigm.
The paper tackled the problem of identifying the most effective form of human saliency for open-set iris presentation attack detection, finding that denoised eye tracking heatmaps provided the best generalization improvement with specific metrics like AUROC and APCER at BPCER of 1%.
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.