Recent studies on deepfake detection have achieved promising results when training and testing faces are from the same dataset. However, their results severely degrade when confronted with forged samples that the model has not yet seen during training. In this paper, deepfake data to help detect deepfakes. this paper present we put a new insight into diffusion model-based data augmentation, and propose a Masked Conditional Diffusion Model (MCDM) for enhancing deepfake detection. It generates a variety of forged faces from a masked pristine one, encouraging the deepfake detection model to learn generic and robust representations without overfitting to special artifacts. Extensive experiments demonstrate that forgery images generated with our method are of high quality and helpful to improve the performance of deepfake detection models.

翻译：近期关于深度伪造检测的研究在训练和测试人脸来自同一数据集时取得了令人满意的结果。然而，当面对训练过程中未被模型见过的伪造样本时，其检测性能会严重下降。本文提出了一种基于扩散模型数据增强的新思路，并设计了一种掩码条件扩散模型（MCDM）来增强深度伪造检测能力。该模型从掩码处理后的原始人脸中生成多样化的伪造人脸，促使深度伪造检测模型学习通用且鲁棒的表示，同时避免过拟合到特定伪影。大量实验证明，使用本方法生成的伪造图像质量高，且有助于提升深度伪造检测模型的性能。