- An RDP (Renyi Differential Privacy) based analytical Moment Accountant implementation that is numerically stable.
- Supports privacy amplification for generic RDP algorithm for subsampling without replacement and poisson sampling.
- Stronger composition than the optimal composition using only (ε,δ)-DP.
- A privacy calibrator that numerically calibrates noise to privacy requirements using RDP.
- Bring Your Own Mechanism: Just implement the RDP of your own DP algorithm as a function.
It's easy. Just run:
pip install autodp
Then follow the Jupyter notebooks in the tutorials
folder to get started.
pip
should automatically install all the dependences for you.- Currently we support only Python3.
- You might need to run
pip3 install autodp --upgrade
- Yu-Xiang Wang, Borja Balle, and Shiva Kasiviswanathan. (2019) "Subsampled Renyi Differential Privacy and Analytical Moments Accountant.". in AISTATS-2019 (Notable Paper Award).
- Yuqing Zhu, Yu-Xiang Wang. (2019) "Poisson Subsampled Renyi Differential Privacy". ICML-2019, to appear.
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.
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.
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
)! Please explain clearly what the contribution is about and attach/cite papers whenever appropriate.