Multimodal generative AI systems like Stable Diffusion, DALL-E, and MidJourney have fundamentally changed how synthetic images are created. These tools drive innovation but also enable the spread of misleading content, false information, and manipulated media. As generated images become harder to distinguish from photographs, detecting them has become an urgent priority. To combat this challenge, We release MS COCOAI, a novel dataset for AI generated image detection consisting of 96000 real and synthetic datapoints, built using the MS COCO dataset. To generate synthetic images, we use five generators: Stable Diffusion 3, Stable Diffusion 2.1, SDXL, DALL-E 3, and MidJourney v6. Based on the dataset, we propose two tasks: (1) classifying images as real or generated, and (2) identifying which model produced a given synthetic image. The dataset is available at https://huggingface.co/datasets/Rajarshi-Roy-research/Defactify_Image_Dataset.

翻译：以Stable Diffusion、DALL-E和MidJourney为代表的多模态生成式AI系统，从根本上改变了合成图像的创建方式。这些工具推动了创新，但也助长了误导性内容、虚假信息和篡改媒体的传播。随着生成图像与真实照片越来越难以区分，检测此类图像已成为一项紧迫任务。为应对这一挑战，我们发布了MS COCOAI——一个基于MS COCO数据集构建的新型AI生成图像检测数据集，包含96,000个真实与合成数据点。我们使用五种生成器来合成图像：Stable Diffusion 3、Stable Diffusion 2.1、SDXL、DALL-E 3和MidJourney v6。基于该数据集，我们提出两项任务：(1) 将图像分类为真实或生成图像；(2) 识别给定合成图像是由哪个模型生成的。数据集可通过 https://huggingface.co/datasets/Rajarshi-Roy-research/Defactify_Image_Dataset 获取。