hsam-2021/deepfake-detection

I present a web based application for automatic detection of replacement and reenactment of deep fakes. I worked on a novel Res-Next convolution neural network for face reenactment which works for pose and expression variations and can be applied to single image or a video sequence.

27
/ 100
Experimental

This project provides a web application to automatically detect deepfakes, specifically identifying face replacement and reenactment in videos. You upload a short video, and the system tells you whether it's a genuine video or a deepfake. This tool is for anyone concerned with verifying the authenticity of video content, such as journalists, fact-checkers, or social media analysts.

No commits in the last 6 months.

Use this if you need a quick, automated way to check if a video has been manipulated using deepfake technology.

Not ideal if you need to detect extremely high-quality, expertly crafted deepfakes with minimal artifacts, as the current model might struggle with those.

video-authenticity deepfake-detection media-verification content-integrity digital-forensics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

11

Forks

3

Language

Jupyter Notebook

License

Last pushed

Jan 13, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hsam-2021/deepfake-detection"

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