athen-lab/mai

Multilayer Authenticity Identifier (MAI), a CNN model that attempts to identify synthetic AI images.

27
/ 100
Experimental

This project helps anyone who needs to determine if an image is real or was generated by artificial intelligence. It takes an image, ideally 200x200 pixels, and provides a score indicating its likelihood of being AI-generated, with a score of 1 meaning it's absolutely synthetic and 0 meaning it's authentic. Journalists, content creators, or researchers can use this to verify image origins.

No commits in the last 6 months.

Use this if you need to quickly assess the authenticity of a single image and suspect it might be AI-generated.

Not ideal if you need a solution for identifying AI-generated content across various media types beyond just images, or if you require an extremely high degree of certainty for critical applications.

image-verification content-authenticity media-literacy digital-forensics fake-news-detection
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

31

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Feb 15, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/athen-lab/mai"

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