From 4b6a60dfdb615e80f2ec8e137d81ad532162aaef Mon Sep 17 00:00:00 2001 From: "A. Unique TensorFlower" Date: Wed, 24 Jun 2020 08:34:39 -0700 Subject: [PATCH] Mention codelab in the README file. PiperOrigin-RevId: 318069426 --- .../privacy/membership_inference_attack/README.md | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/tensorflow_privacy/privacy/membership_inference_attack/README.md b/tensorflow_privacy/privacy/membership_inference_attack/README.md index 840b81c..2380a68 100644 --- a/tensorflow_privacy/privacy/membership_inference_attack/README.md +++ b/tensorflow_privacy/privacy/membership_inference_attack/README.md @@ -16,7 +16,15 @@ The tests provided by the library are "black box". That is, only the outputs of the model are used (e.g., losses, logits, predictions). Neither model internals (weights) nor input samples are required. -## Highest level -- get attack summary +## How to use + +### Codelab + +The easiest way to get started is to go through [the introductory codelab](https://github.com/tensorflow/privacy/blob/master/tensorflow_privacy/privacy/membership_inference_attack/codelab.ipynb). +This trains a simple image classification model and tests it against a series +of membership inference attacks. + +For a more detailed overview of the library, please check the sections below. ### Basic usage