Detecting diffusion-generated images has recently grown into an emerging research area. Existing diffusion-based datasets predominantly focus on general image generation. However, facial forgeries, which pose a more severe social risk, have remained less explored thus far. To address this gap, this paper introduces DiFF, a comprehensive dataset dedicated to face-focused diffusion-generated images. DiFF comprises over 500,000 images that are synthesized using thirteen distinct generation methods under four conditions. In particular, this dataset leverages 30,000 carefully collected textual and visual prompts, ensuring the synthesis of images with both high fidelity and semantic consistency. We conduct extensive experiments on the DiFF dataset via a human test and several representative forgery detection methods. The results demonstrate that the binary detection accuracy of both human observers and automated detectors often falls below 30%, shedding light on the challenges in detecting diffusion-generated facial forgeries. Furthermore, we propose an edge graph regularization approach to effectively enhance the generalization capability of existing detectors.

翻译：检测扩散生成的图像近年来已成为一个新兴的研究领域。现有基于扩散的数据集主要集中在通用图像生成方面。然而，面部伪造这一对社会风险更为严重的问题，目前仍鲜有研究。为填补这一空白，本文引入了DiFF，一个专门针对扩散生成面部图像的综合性数据集。DiFF包含超过50万张图像，这些图像采用13种不同的生成方法在四种条件下合成。特别地，该数据集利用了精心收集的3万个文本和视觉提示，确保合成图像兼具高保真度和语义一致性。我们在DiFF数据集上通过人类测试和几种代表性伪造检测方法进行了广泛实验。结果表明，无论是人类观察者还是自动检测器，其二元检测准确率通常低于30%，这揭示了检测扩散生成面部伪造的挑战性。此外，我们提出了一种边缘图正则化方法，以有效增强现有检测器的泛化能力。