An advanced Differential Privacy library for pyTorch, based on opacus.

Jens Keim a39ff65a6a allow lists or tuples for weights as well		преди 3 години
LICENSE-2.0.txt	cf57afea64 add license	преди 3 години
LICENSE.md	cf57afea64 add license	преди 3 години
README.md	a88815e07c fix readme formatting for gogs	преди 3 години
privacy_engine_xl.py	a39ff65a6a allow lists or tuples for weights as well	преди 3 години

aDPtorch

An advanced Differential Privacy library for pyTorch, based on opacus.

Current Features

privacy_engine_xl
- additional noise distributions
  - Gauss (Normal)
  - Laplace
  - Exponential
- server side noise generation function

This repository is licensed under the Apache License 2.0, as some of the code is derived from opacus.

This repo contains a markdown and a text version of the license.

In case of any inconstancies refer to the license's website.