Abstract
Face recognition technology has become an integral part of modern security systems and user authentication processes. However, these systems are vulnerable to spoofing attacks and can easily be circumvented. Most prior research in face anti-spoofing (FAS) approaches it as a two-class classification task where models are trained on real samples and known spoof attacks and tested for detection performance on unknown spoof attacks. However, in practice, FAS should be treated as a one-class classification task where, while training, one cannot assume any knowledge regarding the spoof samples a priori. In this paper, we reformulate the face anti-spoofing task from a one-class perspective and propose a novel hyperbolic one-class classification framework. To train our network, we use a pseudo-negative class sampled from the Gaussian distribution with a weighted running mean and propose two novel loss functions: (1) Hyp-PC: Hyperbolic Pairwise Confusion loss, and (2) Hyp-CE: Hyperbolic Cross Entropy loss, which operate in the hyperbolic space. Additionally, we employ Euclidean feature clipping and gradient clipping to stabilize the training in the hyperbolic space. To the best of our knowledge, this is the first work extending hyperbolic embeddings for face anti-spoofing in a one-class manner. With extensive experiments on five benchmark datasets: Rose-Youtu, MSU-MFSD, CASIA-MFSD, Idiap Replay-Attack, and OULU-NPU, we demonstrate that our method significantly outperforms the state-of-the-art, achieving better spoof detection performance.
Abstract (translated)
面部识别技术已成为现代安全系统和用户身份验证过程的重要组成部分。然而,这些系统容易受到伪造攻击的攻击,而且可以轻松被绕过。在先前的面部抗伪造(FAS)研究中,大多数将FAS视为二分类分类任务,其中模型在真实样本和已知伪造攻击上进行训练,并在未知伪造攻击上测试检测性能。然而,在实践中,FAS应该被视为一个一分类分类任务,在训练过程中,不能假设有任何关于伪造样本的知识。在本文中,我们将从一分类的角度重新定义面部抗伪造任务,并提出了一个新的超几何一分类框架。为了训练我们的网络,我们使用从高斯分布伪负样本,带权运行平均的伪负类,并提出两个新的损失函数:(1) Hyp-PC:超几何对偶混淆损失,和(2) Hyp-CE:超几何交叉熵损失,它们在超几何空间中操作。此外,我们还使用欧氏特征截断和梯度截断来稳定超几何空间中的训练。据我们所知,这是第一个在一类方式上扩展超几何嵌入用于面部抗伪造的工作。在五个基准数据集:罗切斯特县,密苏里大学MSU-MFSD,卡西娅大学CASIA-MFSD,碘亚帕回复攻击和OULU-NPU的广泛实验中,我们证明了我们的方法在性能上明显优于现有技术水平,实现了更好的伪造检测性能。
URL
https://arxiv.org/abs/2404.14406
