Biometric systems are vulnerable to Presentation Attacks (PA) performed using various Presentation Attack Instruments (PAIs). Even though there are numerous Presentation Attack Detection (PAD) techniques based on both deep learning and hand-crafted features, the generalization of PAD for unknown PAI is still a challenging problem. In this work, we empirically prove that the initialization of the PAD model is a crucial factor for the generalization, which is rarely discussed in the community. Based on such observation, we proposed a self-supervised learning-based method, denoted as DF-DM. Specifically, DF-DM is based on a global-local view coupled with De-Folding and De-Mixing to derive the task-specific representation for PAD. During De-Folding, the proposed technique will learn region-specific features to represent samples in a local pattern by explicitly minimizing generative loss. While De-Mixing drives detectors to obtain the instance-specific features with global information for more comprehensive representation by minimizing interpolation-based consistency. Extensive experimental results show that the proposed method can achieve significant improvements in terms of both face and fingerprint PAD in more complicated and hybrid datasets when compared with state-of-the-art methods. When training in CASIA-FASD and Idiap Replay-Attack, the proposed method can achieve an 18.60% Equal Error Rate (EER) in OULU-NPU and MSU-MFSD, exceeding baseline performance by 9.54%. The source code of the proposed technique is available at https://github.com/kongzhecn/dfdm.

翻译：生物识别系统易受到使用各种展示攻击工具（PAI）进行的展示攻击（PA）。尽管基于深度学习和手工特征的展示攻击检测（PAD）技术众多，但针对未知PAI的PAD泛化能力仍是一个具有挑战性的问题。本研究通过实验证明，PAD模型的初始化为影响泛化性能的关键因素，而该因素在学界鲜有讨论。基于此发现，我们提出一种基于自监督学习的方法，命名为DF-DM。具体而言，DF-DM采用全局-局部视图结合解折叠（De-Folding）与解混合（De-Mixing）机制，以推导面向PAD的任务特异性表征。在解折叠过程中，所提技术通过显式最小化生成损失，学习以局部模式表征样本的区域特异性特征；而解混合则通过最小化插值一致性约束，驱动检测器获取包含全局信息的实例特异性特征，以构建更全面的表征。大量实验结果表明，在更复杂和混合的数据集上，所提方法在面部和指纹PAD任务中均能实现显著性能提升。以CASIA-FASD和Idiap Replay-Attack为训练集时，该方法在OULU-NPU和MSU-MFSD上取得18.60%的等错误率（EER），较基线性能提升9.54%。所提技术的源代码已发布于https://github.com/kongzhecn/dfdm。