Research in presentation attack detection (PAD) for iris recognition has largely moved beyond evaluation in “closed-set” scenarios, to emphasize ability to generalize to presentation attack types not present in the training data. This paper offers multiple contributions to understand and extend the state-of-the-art in open-set iris PAD. First, it describes the most authoritative evaluation to date of iris PAD. We have curated the largest publicly-available image dataset for this problem, drawing from 26 benchmarks previously released by various groups, and adding 150,000 images being released with this paper, to create a set of 450,000 images representing authentic iris and seven types of presentation attack instrument (PAI). We formulate a leave-one-PAI-out evaluation protocol, and show that even the best algorithms in the closed-set evaluations exhibit catastrophic failures on multiple attack types in the open-set scenario. This includes algorithms performing well in the most recent LivDet-Iris 2020 competition, which may come from the fact that the LivDet-Iris protocol emphasizes sequestered images rather than unseen attack types. Second, we evaluate the accuracy of five open-source iris presentation attack algorithms available today, one of which is newly-proposed in this paper, and build an ensemble method that beats the winner of the LivDet-Iris 2020 by a substantial margin. This paper demonstrates that closed-set iris PAD, when all PAIs are known during training, is a solved problem, with multiple algorithms showing very high accuracy, while open-set iris PAD, when evaluated correctly, is far from being solved. The newly-created dataset, new open-source algorithms, and evaluation protocol, all made publicly available with this paper, provide experimental artifacts that researchers can use to measure progress on this important problem.

中文翻译：

---

开放式虹膜呈现攻击检测综合研究


用于虹膜识别的演示攻击检测（PAD）研究在很大程度上已经超越了“封闭集”场景中的评估，强调泛化到训练数据中不存在的演示攻击类型的能力。本文为理解和扩展开放式虹膜 PAD 的最新技术做出了多项贡献。首先，它描述了迄今为止最权威的虹膜PAD评测。我们针对这个问题策划了最大的公开可用图像数据集，借鉴了各个组织之前发布的 26 个基准，并添加了本文中发布的 150,000 张图像，创建了一组代表真实虹膜和七种类型的演示攻击的 450,000 张图像。仪器（PAI）。我们制定了留一 PAI 评估协议，并表明，即使是封闭集评估中最好的算法，在开放集场景中的多种攻击类型上也会表现出灾难性的失败。这包括在最近的 LivDet-Iris 2020 竞赛中表现良好的算法，这可能来自于 LivDet-Iris 协议强调隔离图像而不是看不见的攻击类型。其次，我们评估了目前可用的五种开源虹膜呈现攻击算法的准确性，其中一种是本文新提出的，并构建了一种集成方法，以大幅优势击败了 LivDet-Iris 2020 的获胜者。本文证明，当所有 PAI 在训练过程中已知时，闭集虹膜 PAD 是一个已解决的问题，多种算法显示出非常高的精度，而开集虹膜 PAD 在正确评估时，还远未得到解决。 新创建的数据集、新的开源算法和评估协议均随本文公开发布，提供了实验工件，研究人员可以使用它们来衡量这一重要问题的进展。