Timezone: »

 
Exposing the Fake: Effective Diffusion-Generated Images Detection
RuiPeng Ma · Jinhao Duan · Fei Kong · Xiaoshuang Shi · Kaidi Xu

@
in 2nd ICML Workshop on New Frontiers in Adversarial Machine Learning »
Event URL: https://openreview.net/forum?id=7R62e4Wgim »

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 SeDID and neural network-based SeDID, 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 diffusionmodels. Thus, our work makes a pivotal contribution to distinguishing diffusion model-generated images, marking a significant step in the domain of artificial intelligence security.

Keywords: Synthetic Image Detection · Security and Privacy in Image Synthesis · Diffusion Generative Models

Author Information

RuiPeng Ma (University of Electronic Science and Technology of China)
Jinhao Duan (Drexel University)
Fei Kong (University of Electronic Science and Technology of China)
Xiaoshuang Shi (University of Electronic Science and Technology of China)
Kaidi Xu (Drexel University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors