Deepfake detection remains a challenging task due to the difficulty of generalizing to new types of forgeries. This problem primarily stems from the overfitting of existing detection methods to forgery-irrelevant features and method-specific patterns. The latter is often ignored by previous works. This paper presents a novel approach to address the two types of overfitting issues by uncovering common forgery features. Specifically, we first propose a disentanglement framework that decomposes image information into three distinct components: forgery-irrelevant, method-specific forgery, and common forgery features. To ensure the decoupling of method-specific and common forgery features, a multi-task learning strategy is employed, including a multi-class classification that predicts the category of the forgery method and a binary classification that distinguishes the real from the fake. Additionally, a conditional decoder is designed to utilize forgery features as a condition along with forgery-irrelevant features to generate reconstructed images. Furthermore, a contrastive regularization technique is proposed to encourage the disentanglement of the common and specific forgery features. Ultimately, we only utilize the common forgery features for the purpose of generalizable deepfake detection. Extensive evaluations demonstrate that our framework can perform superior generalization than current state-of-the-art methods.

翻译：深度伪造检测因难以泛化至新型伪造手段而仍具挑战性。该问题主要源于现有检测方法过度拟合伪造无关特征及方法特定模式，后者常被先前研究忽视。本文提出一种通过发现通用伪造特征来应对两类过拟合问题的新方法。具体而言，我们首先构建解耦框架，将图像信息分解为三个独立成分：伪造无关特征、方法特定伪造特征及通用伪造特征。为确保方法特定与通用伪造特征的解耦，采用多任务学习策略，包含预测伪造方法类别的多分类任务与区分真伪的二分类任务。此外，设计条件解码器，将伪造特征作为条件与伪造无关特征共同生成重构图像。进一步提出对比正则化技术，促进通用与特定伪造特征的解耦。最终仅利用通用伪造特征实现可泛化的深度伪造检测。广泛评估表明，本框架的泛化性能优于现有最优方法。