This paper explores the task of detecting images generated by text-to-image diffusion models. To evaluate this, we consider images generated from captions in the MSCOCO and Wikimedia datasets using two state-of-the-art models: Stable Diffusion and GLIDE. Our experiments show that it is possible to detect the generated images using simple Multi-Layer Perceptrons (MLPs), starting from features extracted by CLIP, or traditional Convolutional Neural Networks (CNNs). We also observe that models trained on images generated by Stable Diffusion can detect images generated by GLIDE relatively well, however, the reverse is not true. Lastly, we find that incorporating the associated textual information with the images rarely leads to significant improvement in detection results but that the type of subject depicted in the image can have a significant impact on performance. This work provides insights into the feasibility of detecting generated images, and has implications for security and privacy concerns in real-world applications.

翻译：本文探讨了检测由文本到图像扩散模型生成的图像的任务。为了评估这一任务，我们使用两种最先进的模型（Stable Diffusion和GLIDE）基于MSCOCO和Wikimedia数据集中的标题生成了图像。实验表明，从CLIP提取的特征出发，使用简单的多层感知机（MLPs）或传统的卷积神经网络（CNNs）即可检测生成的图像。我们还观察到，在Stable Diffusion生成的图像上训练的模型能够相对较好地检测GLIDE生成的图像，但反之则不然。最后，我们发现将图像相关的文本信息纳入模型很少能显著提升检测结果，但图像主题类型对性能有显著影响。这项工作为检测生成图像的可行性提供了见解，并对现实应用中的安全与隐私问题具有启示意义。