Deepfake videos are becoming increasingly realistic, showing subtle tampering traces on facial areasthat vary between frames. Consequently, many existing Deepfake detection methods struggle to detect unknown domain Deepfake videos while accurately locating the tampered region. To address thislimitation, we propose Delocate, a novel Deepfake detection model that can both recognize andlocalize unknown domain Deepfake videos. Ourmethod consists of two stages named recoveringand localization. In the recovering stage, the modelrandomly masks regions of interest (ROIs) and reconstructs real faces without tampering traces, resulting in a relatively good recovery effect for realfaces and a poor recovery effect for fake faces. Inthe localization stage, the output of the recoveryphase and the forgery ground truth mask serve assupervision to guide the forgery localization process. This process strategically emphasizes the recovery phase of fake faces with poor recovery, facilitating the localization of tampered regions. Ourextensive experiments on four widely used benchmark datasets demonstrate that Delocate not onlyexcels in localizing tampered areas but also enhances cross-domain detection performance.

翻译：深度伪造视频正变得越来越逼真，在帧间变化的面部区域上呈现出微妙的篡改痕迹。因此，许多现有的深度伪造检测方法难以检测未知领域的深度伪造视频，同时准确定位被篡改的区域。为解决这一局限性，我们提出Delocate，一种新型深度伪造检测模型，既能识别也能定位未知领域的深度伪造视频。我们的方法包含两个阶段，分别称为重建和定位。在重建阶段，模型随机掩蔽感兴趣区域（ROI）并重建不含篡改痕迹的真实人脸，从而对真实人脸取得较好的重建效果，对伪造人脸取得较差的重建效果。在定位阶段，重建阶段的输出和伪造真实掩码作为监督，指导伪造定位过程。该过程战略性地强调重建效果差的伪造人脸的重建阶段，从而促进篡改区域的定位。我们在四个广泛使用的基准数据集上进行的大量实验表明，Delocate不仅在篡改区域定位方面表现出色，而且还提升了跨域检测性能。