ar-roy/dct-cryptonets
Official code for "DCT-CryptoNets: Scaling Private Inference in the Frequency Domain" [ICLR 2025]
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.
Stars
10
Forks
2
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
tensorflow/privacy
Library for training machine learning models with privacy for training data
meta-pytorch/opacus
Training PyTorch models with differential privacy
tf-encrypted/tf-encrypted
A Framework for Encrypted Machine Learning in TensorFlow
awslabs/fast-differential-privacy
Fast, memory-efficient, scalable optimization of deep learning with differential privacy
privacytrustlab/ml_privacy_meter
Privacy Meter: An open-source library to audit data privacy in statistical and machine learning...