On The Detection of Synthetic Images Generated by Diffusion Models
By Riccardo Corvi, Davide Cozzolino, Giada Zingarini, Giovanni Poggi, Koki Nagano, Luisa Verdoliva. IEEE International Conference on Acoustics, Speech, and Signal Processing, 2022
423 citations recorded by the source corpus.
Over the past decade, there has been tremendous progress in creating synthetic media, mainly thanks to the development of powerful methods based on generative adversarial networks (GAN). Very recently, methods based on diffusion models (DM) have been gaining the spotlight. In addition to providing an impressive level of photorealism, they enable the creation of text-based visual content, opening up new and exciting opportunities in many different application fields, from arts to video games. On the other hand, this property is an additional asset in the hands of malicious users, who can generate and distribute fake media perfectly adapted to their attacks, posing new challenges to the media forensic community. With this work, we seek to understand how difficult it is to distinguish synthetic images generated by diffusion models from pristine ones and whether current state-of-the-art detectors are suitable for the task. To this end, first we expose the forensics traces left by diffusion models, then study how current detectors, developed for GAN-generated images, perform on these new synthetic images, especially in challenging social-network scenarios involving image compression and resizing. Datasets and code are available at https:github.com/grip-unina/DMimageDetection.
Subfields: Computer Vision and Pattern Recognition, Law
View Paper: https://www.semanticscholar.org/paper/05ce31d0e48c3e700b4fd606dbba3433ea83ab2b
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Ming-Hsuan Yang
- Dacheng Tao
- Yi Yang
- Xiaogang Wang
- Jitendra Malik
- Trevor Darrell
- Richard Zhang
In Law
Citations in the corpus
- Text-to-image Diffusion Models in Generative AI: A Survey (2023, background): “[92], [93] find that the performance of existing detection methods drops significantly on generated images by diffusion models”
- Zero-shot Image-to-Image Translation (2023, background): “However, a line of work has studied whether generated images are detectable, in the context of GANs [65, 36, 12, 59] and more recently, diffusion models [15, 53].”
- DIRE for Diffusion-Generated Image Detection (2023, background): “We note that some recent works also notice the diffusion-generated image detection problem [36, 8].”
- The Stable Signature: Rooting Watermarks in Latent Diffusion Models (2023, neutral): “For comparison, we report results of a state-of-the-art passive method [12], applied on resized and compressed images.”