mikeroyal/Differential-Privacy-Guide
Differential Privacy Guide
This guide helps data scientists and researchers understand and apply differential privacy techniques to protect sensitive user data while still extracting valuable insights. It provides resources on how to introduce 'statistical noise' into datasets to hide individual characteristics without compromising the overall accuracy of analytics. The guide is for anyone who needs to perform data analysis or machine learning on datasets containing personal information, such as customer records or medical data.
No commits in the last 6 months.
Use this if you are a data professional or researcher who needs to analyze sensitive personal data while strictly adhering to privacy regulations and protecting individual identities.
Not ideal if your primary goal is general machine learning model development without a specific focus on differential privacy, or if you are looking for an immediate plug-and-play solution without understanding the underlying concepts.
Stars
20
Forks
1
Language
Python
License
—
Category
Last pushed
Jan 09, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mikeroyal/Differential-Privacy-Guide"
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...