Towards the Detection of Diffusion Model Deepfakes

Jonas Ricker, Simon Damm, Thorsten Holz, Asja Fischer

Keywords: Diffusion Model, Generative Adversarial Network, GAN, Deepfakes, Detection, Frequency Artifact, Frequency Analysis, Spectrum Discrepancies, Synthetic Images, Disinformation, Social Media

TL;DR: We take a first look at the detection of images generated by diffusion models by evaluating state-of-the-art detectors and analyzing DM-generated images in the frequency domain.

Abstract: Diffusion models (DMs) have recently emerged as a promising method in image synthesis. They have surpassed generative adversarial networks (GANs) in both diversity and quality, and have achieved impressive results in text-to-image modeling. However, to date, only little attention has been paid to the detection of DM-generated images, which is critical to prevent adverse impacts on our society. While prior works have shown that GAN-generated images can be reliably detected using automated methods, it is unclear whether the same methods are effective against DMs. In this work, we address this challenge and take a first look at detecting DM-generated images. We approach the problem from two different angles: First, we evaluate the performance of state-of-the-art detectors on a variety of DMs. Second, we analyze DM-generated images in the frequency domain and study different factors that influence the spectral properties of these images. Most importantly, we demonstrate that GANs and DMs produce images with different characteristics, which requires adaptation of existing classifiers to ensure reliable detection. We believe this work provides the foundation and starting point for further research to detect DM deepfakes effectively.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)

Community Implementations: [ 10 code implementations](https://www.catalyzex.com/paper/towards-the-detection-of-diffusion-model/code)