jonasricker/diffusion-model-deepfake-detection

[VISAPP2024] Towards the Detection of Diffusion Model Deepfakes

37
/ 100
Emerging

This project helps researchers and data scientists evaluate how well different deepfake detection methods perform. You input various deepfake images (from diffusion models, GANs, etc.) and pre-trained detection models. The output is a performance report showing metrics like AUROC, helping you understand which detectors are most effective against different types of synthetic images.

103 stars. No commits in the last 6 months.

Use this if you need to benchmark and compare existing deepfake detection algorithms against a variety of synthetic image generation techniques, particularly those from diffusion models.

Not ideal if you're looking for a user-friendly, out-of-the-box application to simply detect deepfakes in your everyday media.

deepfake-detection synthetic-media image-analysis model-evaluation digital-forensics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

103

Forks

11

Language

Python

License

MIT

Last pushed

Nov 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/jonasricker/diffusion-model-deepfake-detection"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.