parham1998/Facial-Privacy-Protection
[CVPR 2025] Official Implementation of the Paper "Enhancing Facial Privacy Protection via Weakening Diffusion Purification"
This tool helps individuals protect their privacy by modifying portrait photos before sharing them online, making it harder for automated face recognition systems to identify them. You input original photos, and it outputs slightly altered versions that look almost identical to the human eye but are designed to confuse facial recognition software. Anyone concerned about their identity being tracked through public photos on social media or other platforms would find this useful.
Use this if you want to share photos online but prevent automated systems from easily identifying individuals in those images, without noticeably changing the photo's appearance.
Not ideal if you need to completely anonymize faces beyond recognition, as this tool focuses on subtle, identity-preserving alterations.
Stars
14
Forks
1
Language
Python
License
—
Category
Last pushed
Dec 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/parham1998/Facial-Privacy-Protection"
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