kunzhan/BrainGuard

AAAI 2025 (Oral), BrainGuard: Privacy-Preserving Multisubject Image Reconstructions from Brain Activities

24
/ 100
Experimental

This project helps neuroscientists and researchers working with Brain-Computer Interfaces reconstruct images of what a person is perceiving directly from their brain activity. It takes fMRI brain scan data from multiple individuals and outputs reconstructed images, without needing to pool sensitive individual data. Researchers in neuroscience, cognitive science, and BCI development would use this to advance brain decoding.

Use this if you need to reconstruct perceived images from fMRI brain activity across multiple subjects while strictly maintaining each individual's data privacy.

Not ideal if you are working with non-fMRI brain activity data or if you only need single-subject image reconstruction and privacy is not a primary concern.

neuroscience brain-computer-interface fMRI-analysis brain-decoding privacy-preserving-AI
No License No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 4 / 25

How are scores calculated?

Stars

21

Forks

1

Language

Python

License

Last pushed

Dec 01, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/kunzhan/BrainGuard"

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