Opacus is a library that enables training PyTorch models with differential privacy. It supports training with minimal code changes required on the client, has little impact on training performance, and allows the client to online track the privacy budget expended at any given moment. Vectorized per-sample gradient computation that is 10x faster than micro batching. Supports most types of PyTorch models and can be used with minimal modification to the original neural network. Open source, modular API for differential privacy research. Everyone is welcome to contribute. ML practitioners will find this to be a gentle introduction to training a model with differential privacy as it requires minimal code changes. Differential Privacy researchers will find this easy to experiment and tinker with, allowing them to focus on what matters.
Features
- Differential Privacy researchers will find this easy to experiment and tinker with
- Train your model with differential privacy
- The MNIST example shows an end-to-end run using Opacus
- Opacus 1.0 introduced many improvements to the library
- This code is released under Apache 2.0
- ML practitioners will find this to be a gentle introduction to training a model with differential privacy
Project Samples
