Skip to main content

Train PyTorch models with Differential Privacy

Project description

Opacus


CircleCI

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.

Target audience

This code release is aimed at two target audiences:

  1. ML practitioners will find this to be a gentle introduction to training a model with differential privacy as it requires minimal code changes.
  2. Differential Privacy researchers will find this easy to experiment and tinker with, allowing them to focus on what matters.

Installation

The latest release of Opacus can be installed via pip:

pip install opacus

OR, alternatively, via conda:

conda install -c conda-forge opacus

You can also install directly from the source for the latest features (along with its quirks and potentially occasional bugs):

git clone https://github.com/pytorch/opacus.git
cd opacus
pip install -e .

Getting started

To train your model with differential privacy, all you need to do is to instantiate a PrivacyEngine and pass your model, data_loader, and optimizer to the engine's make_private() method to obtain their private counterparts.

# define your components as usual
model = Net()
optimizer = SGD(model.parameters(), lr=0.05)
data_loader = torch.utils.data.DataLoader(dataset, batch_size=1024)

# enter PrivacyEngine
privacy_engine = PrivacyEngine()
model, optimizer, data_loader = privacy_engine.make_private(
    module=model,
    optimizer=optimizer,
    data_loader=data_loader,
    noise_multiplier=1.1,
    max_grad_norm=1.0,
)
# Now it's business as usual

The MNIST example shows an end-to-end run using Opacus. The examples folder contains more such examples.

Migrating to 1.0

Opacus 1.0 introduced many improvements to the library, but also some breaking changes. If you've been using Opacus 0.x and want to update to the latest release, please use this Migration Guide

Learn more

Interactive tutorials

We've built a series of IPython-based tutorials as a gentle introduction to training models with privacy and using various Opacus features.

Technical report and citation

The technical report introducing Opacus, presenting its design principles, mathematical foundations, and benchmarks can be found here.

Consider citing the report if you use Opacus in your papers, as follows:

@article{opacus,
  title={Opacus: {U}ser-Friendly Differential Privacy Library in {PyTorch}},
  author={Ashkan Yousefpour and Igor Shilov and Alexandre Sablayrolles and Davide Testuggine and Karthik Prasad and Mani Malek and John Nguyen and Sayan Ghosh and Akash Bharadwaj and Jessica Zhao and Graham Cormode and Ilya Mironov},
  journal={arXiv preprint arXiv:2109.12298},
  year={2021}
}

Blogposts and talks

If you want to learn more about DP-SGD and related topics, check out our series of blogposts and talks:

FAQ

Check out the FAQ page for answers to some of the most frequently asked questions about differential privacy and Opacus.

Contributing

See the CONTRIBUTING file for how to help out. Do also check out the README files inside the repo to learn how the code is organized.

License

This code is released under Apache 2.0, as found in the LICENSE file.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

opacus-1.1.0.tar.gz (102.1 kB view details)

Uploaded Source

Built Distribution

opacus-1.1.0-py3-none-any.whl (174.6 kB view details)

Uploaded Python 3

File details

Details for the file opacus-1.1.0.tar.gz.

File metadata

  • Download URL: opacus-1.1.0.tar.gz
  • Upload date:
  • Size: 102.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.8.0 pkginfo/1.8.2 readme-renderer/34.0 requests/2.27.1 requests-toolbelt/0.9.1 urllib3/1.26.8 tqdm/4.63.0 importlib-metadata/4.11.3 keyring/23.5.0 rfc3986/2.0.0 colorama/0.4.4 CPython/3.7.5

File hashes

Hashes for opacus-1.1.0.tar.gz
Algorithm Hash digest
SHA256 423a0e04bcdf5283d1910220a2841c132ac078dd14b12ce19d0752c89ed11855
MD5 5286f634de87a42764f4100cf1b9233e
BLAKE2b-256 c08c2cc08cf41e8e9ac65ba38e1055431f26728a2da4be3524e11dbaf3162c21

See more details on using hashes here.

Provenance

File details

Details for the file opacus-1.1.0-py3-none-any.whl.

File metadata

  • Download URL: opacus-1.1.0-py3-none-any.whl
  • Upload date:
  • Size: 174.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.8.0 pkginfo/1.8.2 readme-renderer/34.0 requests/2.27.1 requests-toolbelt/0.9.1 urllib3/1.26.8 tqdm/4.63.0 importlib-metadata/4.11.3 keyring/23.5.0 rfc3986/2.0.0 colorama/0.4.4 CPython/3.7.5

File hashes

Hashes for opacus-1.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ea7483b8880ebec813c39a72dced6c98103085eee9eb0fe790096062b2ee6fef
MD5 477d5d4a7ed6f4daee69b3f560c012d0
BLAKE2b-256 ac09faf3e15b56e22e037f5b63461a3cd1e8f6deb9fd5878fc4836a98f7f5f8d

See more details on using hashes here.

Provenance

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page