A Comprehensive Dataset for Human vs. AI Generated Image Detection

TL;DR

This paper introduces MS COCOAI, a large dataset of real and AI-generated images from multiple models, to facilitate detection of synthetic images and distinguish their sources, addressing the rising challenge of misinformation.

Contribution

The paper presents a new comprehensive dataset for AI-generated image detection, including multiple generative models, and defines two key detection tasks to advance research in this area.

Findings

Dataset contains 96,000 images from five generators.

Two detection tasks are proposed: real vs. generated, and source identification.

Dataset is publicly available for research use.

Abstract

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.