leriomaggio/ppml-tutorial
Privacy-Preserving Machine Learning (PPML) Tutorial
This project helps data scientists, machine learning engineers, and researchers train machine learning models even when they cannot directly access or share sensitive data due to strict privacy regulations. It takes raw, confidential datasets that cannot leave their 'silos' and outputs machine learning models with strong privacy guarantees, preventing reconstruction of sensitive training data.
Use this if you need to build machine learning models on highly sensitive data (like medical records or financial information) without compromising individual privacy or violating data protection laws.
Not ideal if your data is not sensitive and can be freely shared, or if you do not require advanced privacy-preserving techniques beyond basic anonymization.
Stars
43
Forks
9
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Dec 08, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/leriomaggio/ppml-tutorial"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
meta-pytorch/opacus
Training PyTorch models with differential privacy
tensorflow/privacy
Library for training machine learning models with privacy for training data
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...