History

Thomas Steinke 10c086c46a Implementation of differentially private second order methods ("Newton's method") for research project. PiperOrigin-RevId: 500821630		2023-01-09 15:22:37 -08:00
..
audit_2020	Remove unused comments related to Python 2 compatibility.	2022-04-21 08:20:08 -07:00
dp_newton	Implementation of differentially private second order methods ("Newton's method") for research project.	2023-01-09 15:22:37 -08:00
GDP_2019	Explicitly import estimator from tensorflow as a separate import instead of	2022-03-30 16:05:01 -07:00
hyperparameters_2022	Remove license from lr_acc.json file.	2022-05-05 16:47:13 -07:00
instahide_attack_2020	Rename jax.experimental.optimizers -> jax.example_libraries.optimizers	2022-08-05 16:24:49 -07:00
mi_lira_2021	COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/privacy/pull/234 from ftramer:truth_serum fe44a0713952ef1615abf032947082eb5c082836	2022-05-09 15:06:13 -07:00
mi_poison_2022	COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/privacy/pull/234 from ftramer:truth_serum fe44a0713952ef1615abf032947082eb5c082836	2022-05-09 15:06:13 -07:00
neuracrypt_attack_2021	Merge pull request #185 from carlini:neuracrypt	2022-02-18 21:10:54 +00:00
pate_2017	Add TensorFlow Privacy BUILD and WORKSPACE files.	2022-02-16 23:30:06 +00:00
pate_2018	[NumPy] Remove references to deprecated NumPy type aliases.	2022-12-22 10:32:59 -08:00
README.md	Add missing licenses.	2019-01-14 16:02:35 -08:00

Research

This folder contains code to reproduce results from research papers. Currently, the following papers are included:

Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data (ICLR 2017): pate_2017
Scalable Private Learning with PATE (ICLR 2018): pate_2018