Image synthesis has seen significant advancements with the advent of diffusion-based generative models like Denoising Diffusion Probabilistic Models (DDPM) and text-to-image diffusion models. Despite their efficacy, there is a dearth of research dedicated to detecting diffusion-generated images, which could pose potential security and privacy risks. This paper addresses this gap by proposing a novel detection method called Stepwise Error for Diffusion-generated Image Detection (SeDID). Comprising statistical-based SeDIDStat and neural network-based SeDIDNNs, SeDID exploits the unique attributes of diffusion models, namely deterministic reverse and deterministic denoising computation errors. Our evaluations demonstrate SeDID's superior performance over existing methods when applied to diffusion models. Thus, our work makes a pivotal contribution to distinguishing diffusion model-generated images, marking a significant step in the domain of artificial intelligence security.
@article{arxiv.2307.06272,
title = {Exposing the Fake: Effective Diffusion-Generated Images Detection},
author = {Ruipeng Ma and Jinhao Duan and Fei Kong and Xiaoshuang Shi and Kaidi Xu},
journal= {arXiv preprint arXiv:2307.06272},
year = {2023}
}