Back-in-Time Diffusion: Unsupervised Detection of Medical Deepfakes
ACM Transactions on Intelligent Systems and Technology · 2025-12-31 · 16 (6) · 1-26
DOI: 10.1145/3744656 ↗At a glance
Journal article in ACM Transactions on Intelligent Systems and Technology, published online on 2025-10-17. Written by Fred M. Grabovski and 3 co-authors. Cited 10 times so far (Crossref); 83 references. Funded by: European Union’s Horizon 2020 Framework Programme.
Abstract (original language)
Recent progress in generative models has made it easier for a wide audience to edit and create image content, raising concerns about the proliferation of deepfakes, especially in healthcare. Despite the availability of numerous techniques for detecting manipulated images captured by conventional cameras, their applicability to medical images is limited. This limitation stems from the distinctive forensic characteristics of medical images, a result of their imaging process. In this work, we propose a novel anomaly detector for medical imagery based on diffusion models. Normally, diffusion models are used to generate images. However, we show how a similar process can be used to detect synthetic content by making a model reverse the diffusion on a suspected image. We evaluate our method on the task of detecting fake tumors injected and removed from CT and MRI scans. Our method significantly outperforms other state-of-the-art unsupervised detectors with an increased AUC of 0.9 from 0.79 for injection and of 0.96 from 0.91 for removal on average. We also explore our hypothesis using AI explainability tools and publish both our code and new medical deepfake datasets to encourage further research into this domain.
Funding
- European Union’s Horizon 2020 Framework Programme
Cite
APA
Grabovski, F. M., Yasur, L., Amit, G., & Mirsky, Y. (2025). Back-in-Time Diffusion: Unsupervised Detection of Medical Deepfakes. ACM Transactions on Intelligent Systems and Technology, 16(6), 1-26. https://doi.org/10.1145/3744656
Vancouver
Grabovski FM, Yasur L, Amit G, Mirsky Y. Back-in-Time Diffusion: Unsupervised Detection of Medical Deepfakes. ACM Transactions on Intelligent Systems and Technology. 2025;16(6):1-26. doi:10.1145/3744656
BibTeX
@article{Grabovski2025,
author = {Grabovski, Fred M. and Yasur, Lior and Amit, Guy and Mirsky, Yisroel},
title = {Back-in-Time Diffusion: Unsupervised Detection of Medical Deepfakes},
journal = {ACM Transactions on Intelligent Systems and Technology},
year = {2025},
volume = {16},
number = {6},
pages = {1--26},
doi = {10.1145/3744656}
}
EUVIMED