meta-pytorch/opacus
Training PyTorch models with differential privacy
This helps data scientists and machine learning engineers train deep learning models using PyTorch while ensuring the privacy of the underlying data. You input your existing PyTorch model, data loader, and optimizer, and it provides private versions, making your training process differentially private. It's designed for ML practitioners who need to build models without compromising individual data privacy.
1,910 stars. Actively maintained with 3 commits in the last 30 days.
Use this if you are a machine learning practitioner or researcher working with PyTorch and need to ensure your models are trained with strong privacy guarantees, protecting sensitive user data.
Not ideal if you are not using PyTorch for your deep learning projects or if differential privacy is not a requirement for your model training.
Stars
1,910
Forks
389
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Mar 09, 2026
Commits (30d)
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/meta-pytorch/opacus"
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
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...
IBM/differential-privacy-library
Diffprivlib: The IBM Differential Privacy Library