The low-cost, user-friendly, and convenient nature of Automatic Fingerprint Recognition Systems (AFRS) makes them suitable for a wide range of applications. This spreading use of AFRS also makes them vulnerable to various security threats. Presentation Attack (PA) or spoofing is one of the threats which is caused by presenting a spoof of a genuine fingerprint to the sensor of AFRS. Fingerprint Presentation Attack Detection (FPAD) is a countermeasure intended to protect AFRS against fake or spoof fingerprints created using various fabrication materials. In this paper, we have proposed a Convolutional Neural Network (CNN) based technique that uses a Generative Adversarial Network (GAN) to augment the dataset with spoof samples generated from the proposed Open Patch Generator (OPG). This OPG is capable of generating realistic fingerprint samples which have no resemblance to the existing spoof fingerprint samples generated with other materials. The augmented dataset is fed to the DenseNet classifier which helps in increasing the performance of the Presentation Attack Detection (PAD) module for the various real-world attacks possible with unknown spoof materials. Experimental evaluations of the proposed approach are carried out on the Liveness Detection (LivDet) 2015, 2017, and 2019 competition databases. An overall accuracy of 96.20\%, 94.97\%, and 92.90\% has been achieved on the LivDet 2015, 2017, and 2019 databases, respectively under the LivDet protocol scenarios. The performance of the proposed PAD model is also validated in the cross-material and cross-sensor attack paradigm which further exhibits its capability to be used under real-world attack scenarios.

翻译：自动指纹识别系统（AFRS）因其低成本、用户友好及便捷性而适用于广泛的应用场景。AFRS的普及化应用也使其面临多种安全威胁。呈现攻击（PA）或欺骗是一种通过向AFRS传感器呈现伪造的真实指纹所引发的威胁。指纹呈现攻击检测（FPAD）是一种旨在保护AFRS免受使用各种伪造材料制作的虚假或欺骗指纹侵害的对抗措施。本文提出了一种基于卷积神经网络（CNN）的技术，该技术利用生成对抗网络（GAN）通过所提出的开放式补丁生成器（OPG）生成的欺骗样本来扩充数据集。此OPG能够生成逼真的指纹样本，这些样本与使用其他材料生成的现有欺骗指纹样本毫无相似之处。扩充后的数据集被输入DenseNet分类器，这有助于提升呈现攻击检测（PAD）模块针对可能使用未知欺骗材料实施的各种真实世界攻击的性能。该方法的实验评估在活体检测（LivDet）2015、2017及2019竞赛数据库上进行。在LivDet协议场景下，所提方法在LivDet 2015、2017及2019数据库上分别取得了96.20%、94.97%和92.90%的总体准确率。该PAD模型在跨材料与跨传感器攻击范式下的性能也得到了验证，进一步展示了其在真实攻击场景中的适用性。