In the course of the past few years, diffusion models (DMs) have reached an unprecedented level of visual quality. However, relatively little attention has been paid to the detection of DM-generated images, which is critical to prevent adverse impacts on our society. In contrast, generative adversarial networks (GANs), have been extensively studied from a forensic perspective. In this work, we therefore take the natural next step to evaluate whether previous methods can be used to detect images generated by DMs. Our experiments yield two key findings: (1) state-of-the-art GAN detectors are unable to reliably distinguish real from DM-generated images, but (2) re-training them on DM-generated images allows for almost perfect detection, which remarkably even generalizes to GANs. Together with a feature space analysis, our results lead to the hypothesis that DMs produce fewer detectable artifacts and are thus more difficult to detect compared to GANs. One possible reason for this is the absence of grid-like frequency artifacts in DM-generated images, which are a known weakness of GANs. However, we make the interesting observation that diffusion models tend to underestimate high frequencies, which we attribute to the learning objective.

翻译：过去几年中，扩散模型（DMs）在视觉质量上达到了前所未有的水平。然而，针对DM生成图像的检测研究相对较少，而这对于防止其对社会造成负面影响至关重要。相比之下，生成对抗网络（GANs）已从取证角度得到广泛研究。因此，本文顺理成章地评估了以往方法是否可用于检测DM生成的图像。实验得出两个关键发现：（1）最先进的GAN检测器无法可靠区分真实图像与DM生成图像，但（2）在DM生成图像上重新训练这些检测器可实现近乎完美的检测，且这一能力甚至能泛化至GAN检测。结合特征空间分析，我们的结果提出一个假设：与GAN相比，DM产生的可检测伪影更少，因此更难被检测。可能的原因之一是DM生成图像中不存在网格状频率伪影——这类伪影是GAN的已知缺陷。然而，我们有趣地观察到扩散模型倾向于低估高频成分，这归因于其学习目标。