Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.
Project description
Privacy Meter
Introduction
Privacy Meter is an open-source library to audit data privacy in statistical and machine learning algorithms. The tool can help in data protection impact assessment process by providing a quantitative analysis of fundamental privacy risks of a (machine learning) model. It uses state-of-the-art inference techniques to audit a wide range of machine learning algorithms for classification, regression, computer vision, and natural language processing. Privacy Meter generates extensive reports about the aggregate and individual privacy risks for data records in the training set, at multiple levels of access to the model.
Installation
Privacy Meter supports Python >=3.6
and works with tensorflow>=2.4.0
and torch>=1.10.0
.
You can install privacy_meter
using pip
for the latest stable version of the tool:
pip install privacy_meter
Privacy Meter has been tested with other machine learning libraries like HuggingFace and Intel OpenVINO, and can even be extended to be used with a framework of your choice.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for privacy_meter-1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7a7658df216aa9ae077397946dab46c109e5821d8b55f054f7eaade94baadefa |
|
MD5 | e280e95d3833f26af1336455373a5e76 |
|
BLAKE2b-256 | d9356219220c826331a3885a0c162b6c5652b925090cf28c2b924896e0bf6a1c |