dingsheng-ong/ipr-gan

This is the code repo of our CVPR2021 on protecting the IPR of Generative Adversarial Networks (GANs) from Ambiguity Attack

40
/ 100
Emerging

This project helps MLaaS (Machine Learning as a Service) providers protect the intellectual property of their Generative Adversarial Networks (GANs). It takes an existing GAN model and embeds a hidden watermark without affecting its performance, ensuring that unauthorized replication or redistribution can be detected. This tool is for businesses and researchers who deploy GANs to generate content or perform tasks like image super-resolution and style transfer.

No commits in the last 6 months.

Use this if you are a Machine Learning as a Service provider or a researcher who needs to protect your proprietary GAN models from unauthorized use and intellectual property theft.

Not ideal if your deep learning models are not GANs, or if you are looking for general copyright enforcement rather than a technical solution for model protection.

intellectual-property-protection machine-learning-as-a-service generative-adversarial-networks digital-rights-management computer-vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

33

Forks

9

Language

Python

License

BSD-3-Clause

Last pushed

Oct 17, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dingsheng-ong/ipr-gan"

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