Back-in-Time Diffusion: Unsupervised Detection of Medical Deepfakes
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913555863830528 |
|---|---|
| author | Grabovski, Fred Yasur, Lior Amit, Guy Mirsky, Yisroel |
| author_facet | Grabovski, Fred Yasur, Lior Amit, Guy Mirsky, Yisroel |
| contents | 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 our code and new medical deepfake datasets to encourage further research into this domain. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_15169 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Back-in-Time Diffusion: Unsupervised Detection of Medical Deepfakes Grabovski, Fred Yasur, Lior Amit, Guy Mirsky, Yisroel Image and Video Processing Cryptography and Security Computer Vision and Pattern Recognition 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 our code and new medical deepfake datasets to encourage further research into this domain. |
| title | Back-in-Time Diffusion: Unsupervised Detection of Medical Deepfakes |
| topic | Image and Video Processing Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.15169 |