ar-roy/dct-cryptonets

Official code for "DCT-CryptoNets: Scaling Private Inference in the Frequency Domain" [ICLR 2025]

34
/ 100
Emerging

This project helps you perform image analysis using neural networks while keeping the original images completely private and encrypted. You provide encrypted images, and the system delivers encrypted analysis results, ensuring sensitive visual data is never exposed. This is designed for organizations and individuals who need to analyze large volumes of image data, such as medical scans or personal photos, without compromising privacy.

No commits in the last 6 months.

Use this if you need to run deep learning models on sensitive image data (like medical images or personal photos) and absolutely must maintain the privacy of the images throughout the analysis process.

Not ideal if your primary concern is raw speed or if privacy is not a critical requirement, as encryption adds computational overhead.

privacy-preserving AI secure image analysis healthcare AI confidential computing encrypted deep learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

10

Forks

2

Language

Python

License

MIT

Last pushed

Feb 25, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ar-roy/dct-cryptonets"

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