yuxiangw / autodp

autodp: A flexible and easy-to-use package for differential privacy
Apache License 2.0
265 stars 53 forks source link

autodp: Automating differential privacy computation

Highlights

All new autodp "Mechanism" API

The three main classes of the autodp 'mechanism' API.

New features that come with the new API

  1. Object oriented design: see check out autodp_core.py
  2. Zoos are open with many private animals: mechanism_zoo, transformer_zoo, calibrator_zoo.
  3. Added support for f-DP and privacy profile alongside RDP.
  4. Stronger RDP to (eps,delta)-DP conversion.
  5. Privacy amplification by X.
  6. Exactly tight privacy accounting for Gaussian mechanisms and their compositions.
  7. Interpretable privacy guarantee via Hypothesis testing interpretation for any Mechanism.

The new API makes it extremely easy to obtain state-of-the-art privacy guarantees for your favorite randomized mechanisms, with just a few lines of codes.

How to use?

It's easy. Just run:

pip install autodp

or

pip3 install autodp

Check out the Jupyter notebooks in the tutorials folder to get started.

Notes:

To use the current version at the master branch

Install it locally by:

pip install -e .

Research Papers:

How to Contribute?

Follow the standard practice. Fork the repo, create a branch, develop the edit and send a pull request. One of the maintainers are going to review the code and merge the PR. Alternatively, please feel free to creat issues to report bugs, provide comments and suggest new features.

At the moment, contributions to examples, tutorials, as well as the RDP of currently unsupported mechanisms are most welcome (add them to RDP_bank.py)! Also, you may add new mechanisms to mechanism_zoo.py. Contributions to transformer_zoo.py and calibrator_zoo.py are trickier, please email us!

Please explain clearly what the contribution is about in the PR and attach/cite papers whenever appropriate.

Legacy: the moments accountant API from autodp v.0.11 is still supported:

  1. An RDP (Renyi Differential Privacy) based analytical Moment Accountant implementation that is numerically stable.
  2. Supports privacy amplification for generic RDP algorithm for subsampling without replacement and poisson sampling.
  3. Stronger composition than the optimal composition using only (ε,δ)-DP.
  4. A privacy calibrator that numerically calibrates noise to privacy requirements using RDP.
  5. Bring Your Own Mechanism: Just implement the RDP of your own DP algorithm as a function.

Examples:

Composing Subsampled Gaussian Mechanisms (high noise)Composing Subsampled Gaussian Mechanisms (low noise)

Figure 1: Composing subsampled Gaussian Mechanisms. Left: High noise setting with σ=5, γ=0.001, δ=1e-8. Right: Low noise setting with σ=0.5, γ=0.001, δ=1e-8.

Composing Subsampled Laplace Mechanisms (high noise)Composing Subsampled Laplace Mechanisms (low noise)

Figure 2: Composing subsampled Laplace Mechanisms. Left: High noise setting with b=2, γ=0.001, δ=1e-8. Right: Low noise setting with b=0.5, γ=0.001, δ=1e-8.