Abstract
Generalizing deepfake detection to unseen manipulations remains a key challenge. A recent approach to tackle this issue is to train a network with pristine face images that have been manipulated with hand-crafted artifacts to extract more generalizable clues. While effective for static images, extending this to the video domain is an open issue. Existing methods model temporal artifacts as frame-to-frame instabilities, overlooking a key vulnerability: the violation of natural motion dependencies between different facial regions. In this paper, we propose a synthetic video generation method that creates training data with subtle kinematic inconsistencies. We train an autoencoder to decompose facial landmark configurations into motion bases. By manipulating these bases, we selectively break the natural correlations in facial movements and introduce these artifacts into pristine videos via face morphing. A network trained on our data learns to spot these sophisticated biomechanical flaws, achieving state-of-the-art generalization results on several popular benchmarks.
Abstract (translated)
将深度伪造检测推广到未见过的操纵仍然是一个关键挑战。最近的一个方法是通过使用手工制作的艺术品来处理原始面部图像，以提取更通用的线索，从而训练网络解决这一问题。尽管这种方法对静态图像有效，但将其扩展到视频领域仍是一个开放性的问题。现有方法将时间上的伪迹建模为帧与帧之间的不稳定性，忽略了关键漏洞：不同面部区域之间自然运动依赖性的破坏。 在本文中，我们提出了一种合成视频生成方法，该方法通过创建具有微妙的力学不一致性的训练数据来解决这个问题。我们训练一个自动编码器将面部标志配置分解成运动基元。通过对这些基元进行操作，我们可以有选择地打破面部动作之间的自然相关性，并通过面部变形将其伪迹引入原始视频中。在我们的数据上经过训练的网络能够识别这些复杂的生物力学缺陷，在几个流行的基准测试中达到了最先进的泛化结果。
URL
https://arxiv.org/abs/2512.04175
