Exploring techniques to distinguish between real images and those generated using stable diffusion XL
Benjamin Sanders, David Morrison, David Harris-Birtill
TL;DR
This paper explores methods to detect images generated by Stable Diffusion XL using a custom CNN and a new dataset.
Contribution
The paper introduces a novel CNN and a large public dataset of Stable Diffusion XL-generated images for synthetic image detection.
Findings
A custom CNN achieved 97.24% accuracy in distinguishing real and synthetic images.
The dataset is the largest public collection of Stable Diffusion XL-generated images.
ResNet-18 baseline achieved 98.38% accuracy in synthetic image detection.
Abstract
The recent development of text-to-image diffusion models has allowed us to quickly generate realistic images from textual prompts. Despite enabling innovation in particular domains, concerns have been raised over the prospect of malicious users posing synthetic images as genuine. To assess if it is possible to discern between real images and those generated using diffusion models, a novel convolutional neural network was built, trained and tested on a bespoke dataset formed of authentic images from the ImageNet dataset and corresponding synthetic images generated using Stable Diffusion XL: an open-source text-to-image diffusion model. With the public release of this dataset, it is currently the largest publicly accessible collection of images generated using Stable Diffusion XL, significantly contributing to future research in this area. The positive results from our experiment…
Click any figure to enlarge with its caption.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13
Figure 14
Figure 15
Figure 16
Figure 17Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsDigital Media Forensic Detection · Generative Adversarial Networks and Image Synthesis · Cell Image Analysis Techniques