Diffusion models (DMs) have recently emerged as a promising method in image synthesis. However, to date, only little attention has been paid to the detection of DM-generated images, which is critical to prevent adverse impacts on our society. In this work, we address this pressing challenge from two different angles: First, we evaluate the performance of state-of-the-art detectors, which are very effective against images generated by generative adversarial networks (GANs), on a variety of DMs. Second, we analyze DM-generated images in the frequency domain and study different factors that influence the spectral properties of these images. Most importantly, we demonstrate that GANs and DMs produce images with different characteristics, which requires adaptation of existing classifiers to ensure reliable detection. We believe this work provides the foundation and starting point for further research to detect DM deepfakes effectively.

翻译：扩散模型（DMs）近期已成为图像合成领域极具前景的方法。然而，目前针对扩散模型生成图像的检测问题仍鲜有关注，这却是防止其对社会造成负面影响的关键所在。本研究从两个不同角度应对这一紧迫挑战：首先，我们评估了当前最先进检测器（这些检测器对生成对抗网络（GANs）生成的图像具有显著检测效果）在各类扩散模型上的表现；其次，我们从频域角度分析扩散模型生成的图像，并探究影响这些图像频谱特性的不同因素。最重要的是，我们证明了GANs与扩散模型生成的图像具有不同特征，因此需要调整现有分类器以确保可靠检测。我们相信，本研究将为有效检测扩散模型深度伪造的后续研究奠定基础并提供起点。