tf-encrypted/tf-encrypted
A Framework for Encrypted Machine Learning in TensorFlow
This framework helps data scientists and machine learning engineers perform training and prediction using machine learning models while keeping the underlying data private. You input your sensitive datasets and a TensorFlow Keras model, and it produces model predictions or a trained model, all without exposing the raw data to any party. This is ideal for scenarios where data privacy is paramount, such as in healthcare or financial services.
1,244 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to build or use machine learning models on sensitive data, but strict privacy regulations or security concerns prevent you from sharing the raw data directly with the model's host or other collaborators.
Not ideal if your primary goal is maximum computational speed and efficiency, as the encryption process adds overhead compared to standard unencrypted machine learning.
Stars
1,244
Forks
213
Language
Python
License
Apache-2.0
Category
Last pushed
Sep 25, 2024
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tf-encrypted/tf-encrypted"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
tensorflow/privacy
Library for training machine learning models with privacy for training data
meta-pytorch/opacus
Training PyTorch models with differential privacy
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...
IBM/differential-privacy-library
Diffprivlib: The IBM Differential Privacy Library