choi403/DiffusionGuard
DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing (ICLR 2025)
This project helps protect your images from unwanted AI-driven modifications, specifically those using diffusion-based inpainting. You provide an original image and a 'mask' indicating areas you want to safeguard. The output is a slightly altered version of your original image that is robust against AI models trying to fill in or change those masked regions. This tool is for anyone concerned about unauthorized or malicious AI editing of their visual content, such as photographers, artists, or content creators.
No commits in the last 6 months.
Use this if you need to make your images resistant to common AI inpainting techniques that could be used to remove or alter parts of them.
Not ideal if you need protection against image manipulations beyond inpainting, or if you prefer a graphical user interface over command-line tools.
Stars
44
Forks
1
Language
Python
License
—
Category
Last pushed
May 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/choi403/DiffusionGuard"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OPTML-Group/Unlearn-Saliency
[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in...
Shilin-LU/VINE
[ICLR 2025] "Robust Watermarking Using Generative Priors Against Image Editing: From...
WindVChen/DiffAttack
An unrestricted attack based on diffusion models that can achieve both good transferability and...
koninik/DiffusionPen
Official PyTorch Implementation of "DiffusionPen: Towards Controlling the Style of Handwritten...
Wuyxin/DISC
(ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation