VectorInstitute/privacy-enhancing-techniques
A collection of demos and utilities prepared ahead of the Vector Institute Privacy Enhancing Techniques (PETs) Bootcamp.
This project provides practical demonstrations and code examples of various privacy-enhancing technologies (PETs). It takes raw datasets and applies techniques like PATE to show how to protect sensitive information while still deriving insights. This is ideal for researchers, data scientists, and practitioners in healthcare, finance, or other sensitive domains who need to understand and implement data privacy measures.
No commits in the last 6 months.
Use this if you need to explore and understand how different privacy-enhancing techniques work in real-world scenarios with example datasets.
Not ideal if you are looking for a production-ready library or a comprehensive, plug-and-play solution for immediate deployment.
Stars
15
Forks
9
Language
Jupyter Notebook
License
—
Category
Last pushed
Sep 22, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/VectorInstitute/privacy-enhancing-techniques"
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...