Overview

This lab helps you learn how to use differential privacy in machine learning using TensorFlow Privacy.

Learning objectives

1. Wrap existing optimizers into their differentially private counterparts using TensorFlow Privacy.
2. Practice checking hyperparameters introduced by differentially private machine learning.
3. Measure the privacy guarantee provided using analysis tools included in TensorFlow Privacy.

Task 0. Setup and requirements

For each lab, you get a new Google Cloud project and set of resources for a fixed time at no cost.

1. Sign in to Qwiklabs using an incognito window.

2. Note the lab's access time (for example, 1:15:00), and make sure you can finish within that time.
   There is no pause feature. You can restart if needed, but you have to start at the beginning.

3. When ready, click Start lab.

4. Note your lab credentials (Username and Password). You will use them to sign in to the Google Cloud Console.

5. Click Open Google Console.

6. Click Use another account and copy/paste credentials for this lab into the prompts.
   If you use other credentials, you'll receive errors or incur charges.

7. Accept the terms and skip the recovery resource page.

Enable the Notebooks API

1. In the Google Cloud Console, on the Navigation menu, click APIs & Services > Library.

2. Search for Notebooks API and press ENTER.

3. Click on the Notebooks API result, and if the API is not enabled, click Enable.

Enable the Vertex AI API

1. In the Google Cloud Console, on the Navigation menu, click Vertex AI > Dashboard.

2. Click ENABLE ALL RECOMMENDED APIS.

Click Check my progress to verify the objective. Enable the Notebooks and Vertex AI APIs

Task 1. Open Vertex AI Workbench instance

1. In the Google Cloud Console, on the Navigation Menu, click Vertex AI > Workbench.

2. On the User-Managed Notebooks page, click CREATE NEW, select TensorFlow Enterprise 2.12 (Intel® MKL-DNN/MKL).

3. Please use the default zone and region: . Leave the remaining settings as they are and then click Create. The new VM will take 2-3 minutes to start.

4. Click Open JupyterLab. A JupyterLab window will open in a new tab.

Click Check my progress to verify the objective. Create Vertex AI Workbench instance

Task 2. Clone a course repo within your Vertex AI Workbench instance

To clone the notebook in your JupyterLab instance:

1. In JupyterLab, open a new terminal window.

2. At the command-line prompt, run the following command:

3. To confirm that you have cloned the repository, double-click on the asl-ml-immersion directory and ensure that you can see its contents. The files for all the Jupyter notebook-based labs throughout this course are available in this directory.

Click Check my progress to verify the objective. Clone course repo within your Vertex AI Platform Notebooks instance

Task 3. Implement Differential Privacy with TensorFlow Privacy

1. In the notebook interface, navigate to asl-ml-immersion > notebooks > responsible_ai > privacy > solutions and open privacy_dpsgd.ipynb.

2. In the notebook interface, click Edit > Clear All Outputs.

3. Carefully read through the notebook instructions and run through the notebook.

Tip: To run the current cell, click the cell and press SHIFT+ENTER. Other cell commands are listed in the notebook UI under Run.

End your lab

When you have completed your lab, click End Lab. Qwiklabs removes the resources you’ve used and cleans the account for you.

You will be given an opportunity to rate the lab experience. Select the applicable number of stars, type a comment, and then click Submit.

The number of stars indicates the following:

• 1 star = Very dissatisfied
• 2 stars = Dissatisfied
• 3 stars = Neutral
• 4 stars = Satisfied
• 5 stars = Very satisfied

You can close the dialog box if you don't want to provide feedback.

For feedback, suggestions, or corrections, please use the Support tab.

Copyright 2022 Google LLC All rights reserved. Google and the Google logo are trademarks of Google LLC. All other company and product names may be trademarks of the respective companies with which they are associated.