Skip to main content

Train PyTorch models with Differential Privacy

Project description

pytorch-dp: Train PyTorch models with Differential Privacy

CircleCI

pytorch-dp 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.

PyTorch Privacy is currently a preview beta and under active development!

Target audience

This code release is aimed at two target audiences:

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

Installation

pip:

pip install pytorch-dp

From source:

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

Getting started

To train your model with differential privacy, all you need to do is to declare a PrivacyEngine and attach it to your optimizer before running, eg:

model = Net()
optimizer = SGD(model.parameters(), lr=0.05)
privacy_engine = PrivacyEngine(
    model,
    batch_size,
    sample_size,
    alphas=[1, 10, 100],
    noise_multiplier=1.3,
    max_grad_norm=1.0,
)
privacy_engine.attach(optimizer)
# Now it's business as usual

The MNIST example contains an end to end run.

Contributing

See the CONTRIBUTING file for how to help out.

References

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

pytorch-dp-0.1b1.tar.gz (37.0 kB view details)

Uploaded Source

Built Distribution

pytorch_dp-0.1b1-py3-none-any.whl (50.5 kB view details)

Uploaded Python 3

File details

Details for the file pytorch-dp-0.1b1.tar.gz.

File metadata

  • Download URL: pytorch-dp-0.1b1.tar.gz
  • Upload date:
  • Size: 37.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/46.4.0 requests-toolbelt/0.9.1 tqdm/4.46.0 CPython/3.7.5

File hashes

Hashes for pytorch-dp-0.1b1.tar.gz
Algorithm Hash digest
SHA256 65452d4754f76652030f3f847e29af72d87435142ee6f628d75e53c728067371
MD5 0300f29ef73f26738d25b25557a3354f
BLAKE2b-256 9b34b42c653095834d4bbd4f6ac97e87e96880b57ad4f91680339a83507b6afc

See more details on using hashes here.

Provenance

File details

Details for the file pytorch_dp-0.1b1-py3-none-any.whl.

File metadata

  • Download URL: pytorch_dp-0.1b1-py3-none-any.whl
  • Upload date:
  • Size: 50.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/46.4.0 requests-toolbelt/0.9.1 tqdm/4.46.0 CPython/3.7.5

File hashes

Hashes for pytorch_dp-0.1b1-py3-none-any.whl
Algorithm Hash digest
SHA256 0a3ed95297efd8619078b02db19d5b2d5f5d6ed38051f4bf847ec2cce69f2af3
MD5 4105e7caf41fd1e392c8b774aedd66c3
BLAKE2b-256 2a30bf42b71ca0d592063c75637ace731ad309bfbfa38aee2967d5be70b599f2

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