用眼动热图提升虹膜活体检测的抗攻击能力
VISER: Visually-Informed System for Enhanced Robustness in Open-Set Iris Presentation Attack Detection
- 用眼动热图替代传统标注，引导深度学习训练
- 在BPCER=1%时，攻击误判率降低至1.2%
- 首次系统对比多种人类感知数据，适合安防研究者
人类视觉先验在虹膜活体检测（PAD）中展现出潜力，尤其在基于显著性引导的深度学习训练中。现有显著性方法包括鼠标点击标注和眼动追踪生成的热图。然而，人类显著性在开放集虹膜PAD中的最优形式仍不明确。本文通过实验比较人工标注、眼动热图、分割掩码及基础模型嵌入，与最先进的深度学习基线在开放集虹膜PAD任务上的表现。在留一攻击类型外的评估范式下，经去噪的眼动热图在交叉熵基础上将攻击误判率（APCER）在真活体误判率（BPCER）为1%时降低至1.2%，表现最佳。本文还提供了训练好的模型、代码和显著性图，以支持可复现性和后续研究。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。