626_privacy/tensorflow_privacy
2
0
Fork 1
Code Issues Pull requests 1 Projects Releases Packages Wiki Activity Actions
tensorflow_privacy/tensorflow_privacy/privacy/privacy_tests
History
David Marn 03014d0e99 Adds an init file to secret sharer. 
PiperOrigin-RevId: 416819054
2021-12-16 08:38:46 -08:00
..
membership_inference_attack Allows one to run a test on probabilities alone. 2021-11-11 02:17:00 -08:00
secret_sharer Adds an init file to secret sharer. 2021-12-16 08:38:46 -08:00
__init__.py Add init file for privacy_tests. 2021-06-29 17:04:54 -07:00
README.md Moving membership_inference_attack to privacy_tests/membership_inference_attack 2021-06-07 01:11:54 -07:00

README.md

Privacy tests

A good privacy-preserving model learns from the training data, but doesn't memorize individual samples. Excessive memorization is not only harmful for the model predictive power, but also presents a privacy risk.

This library provides empirical tests for measuring potential memorization.