Metadata-Version: 2.1
Name: dp-accounting
Version: 0.3.0
Summary: Tools for tracking differential privacy budgets
Home-page: https://github.com/google/differential-privacy/
Author: Google Differential Privacy Team
Author-email: dp-open-source@google.com
License: Apache 2.0
Keywords: differential-privacy accounting
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.7
Description-Content-Type: text/markdown

# Differential Privacy Accounting

This directory contains tools for tracking differential privacy budgets,
available as part of the
[Google differential privacy library](https://github.com/google/differential-privacy).

The set of DpEvent classes allow you to describe complex differentially private
mechanisms such as Laplace and Gaussian, subsampling mechanisms, and their
compositions. The PrivacyAccountant classes can ingest DpEvents and return the
ε, δ of the composite mechanism. Privacy Loss Distributions (PLDs) and RDP
accounting are currently supported.

More detailed definitions and references about PLDs can be found
[in our supplementary pdf document](https://github.com/google/differential-privacy/tree/main/common_docs/Privacy_Loss_Distributions.pdf).

We test this library on Linux with Python version 3.7. If you experience any
problems, please file an issue on GitHub, also for other platforms or Python
versions.

