dessa-oss/DeepFake-Detection

Towards deepfake detection that actually works

51
/ 100
Established

This project helps media analysts, journalists, or content moderators identify deepfake videos more reliably. It takes video files as input and outputs a prediction of whether the video contains real-world deepfake manipulation or other synthetic video techniques. This tool is for professionals who need to verify video authenticity, especially in contexts where deepfakes are becoming increasingly sophisticated.

643 stars. No commits in the last 6 months.

Use this if you need a robust deepfake detection system that performs well on diverse, real-world manipulated videos, rather than just academic datasets.

Not ideal if you lack significant computing power (GPU and 32GB+ RAM) or if you are looking for an out-of-the-box, user-friendly application without technical setup.

video-verification digital-forensics content-moderation media-authenticity misinformation-detection
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

643

Forks

199

Language

Python

License

MIT

Last pushed

Nov 22, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dessa-oss/DeepFake-Detection"

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