sisaman/GAP
GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation (USENIX Security '23)
This project helps machine learning researchers and practitioners evaluate the performance of differentially private graph neural networks. It takes a graph dataset (like social networks or recommendation graphs) and outputs privacy-preserving models with performance metrics, demonstrating how to train and compare them. It's designed for those exploring or implementing privacy-preserving machine learning on graph data.
No commits in the last 6 months.
Use this if you are a machine learning researcher or engineer working with graph data and need to build or evaluate models that protect individual privacy using differential privacy.
Not ideal if you are looking for a plug-and-play solution for general data privacy or do not have experience working with graph neural networks or machine learning frameworks like PyTorch.
Stars
49
Forks
16
Language
Jupyter Notebook
License
CC0-1.0
Category
Last pushed
Jul 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sisaman/GAP"
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...