Project description

Privacy Accounting

This directory contains tools for tracking privacy budgets. Currently, it provides an implementation of Privacy Loss Distributions (PLDs) which can help compute an accurate estimate of the total ε, δ across multiple executions of differentially private queries. Our implementation currently supports Laplace Mechanism, Gaussian Mechanism and Randomized Response. A supplementary material with more detailed definitions and references can be found here.

Project details

These details have not been verified by PyPI

Project links

Homepage

GitHub Statistics

View statistics for this project via Libraries.io, or by using our public dataset on Google BigQuery

Release history Release notifications | RSS feed

0.4.3

Sep 19, 2023

0.4.2

Jun 20, 2023

0.4.1

Apr 26, 2023

0.4.0

Mar 30, 2023

0.3.0

Aug 25, 2022

0.1.2

Jul 18, 2022

0.1.1

Jul 12, 2022

0.1.0

Jun 14, 2022

0.0.2

Oct 1, 2021

This version

0.0.1

Nov 17, 2020

Download files

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

Source Distribution

dp-accounting-0.0.1.tar.gz (21.4 kB view hashes)

Uploaded Nov 17, 2020 Source

Built Distribution

dp_accounting-0.0.1-py3-none-any.whl (27.5 kB view hashes)

Uploaded Nov 17, 2020 Python 3

Hashes for dp-accounting-0.0.1.tar.gz

Hashes for dp-accounting-0.0.1.tar.gz
Algorithm	Hash digest
SHA256	`da52f32645bcaf94cf1cf5f0920187a76fc900fbbdaff79532a54e39f70cc248`
MD5	`4d109abe7b64f1015c47e99830db2cec`
BLAKE2b-256	`7da13af6f74ac5840424f459c1be6fa2fda2bd1cd607631f27c5292eafc40663`

Hashes for dp_accounting-0.0.1-py3-none-any.whl

Hashes for dp_accounting-0.0.1-py3-none-any.whl
Algorithm	Hash digest
SHA256	`b3eec0da9a4a97ad9d7bd2d0dbecde4238f4c19774ffe330fd3ae1afa07ecf95`
MD5	`842b6564fb171a3b53f90dce72eb40a2`
BLAKE2b-256	`1a4decf064821ed25ff996c3b4fc6114db286370c13ad4b951f5487ab705b243`