Training with Sample-Level Differential Privacy using TensorFlow-Privacy Engine#

View on GitHub

In this example, we demonstrate how to train a model with sample-level differential privacy (DP) using Flower. We employ TensorFlow and integrate the tensorflow-privacy Engine to achieve sample-level differential privacy. This setup ensures robust privacy guarantees during the client training phase.

For more information about DP in Flower please refer to the tutorial. For additional information about tensorflow-privacy, visit the official website.

Environments Setup#

Start by cloning the example. We prepared a single-line command that you can copy into your shell which will checkout the example for you:

git clone --depth=1 && mv flower/examples/tensorflow-privacy . && rm -rf flower && cd tensorflow-privacy

This will create a new directory called tensorflow-privacy containing the following files:

-- pyproject.toml

Installing dependencies#

Project dependencies are defined in pyproject.toml. Install them with:

pip install .

Run Flower with tensorflow-privacy and TensorFlow#

2. Start the long-running Flower clients (SuperNodes)#

Start 2 Flower SuperNodes in 2 separate terminal windows, using:

flower-client-app client:appA --insecure
flower-client-app client:appB --insecure

tensorflow-privacy hyperparameters can be passed for each client in ClientApp instantiation (in In this example, noise_multiplier=1.5 and noise_multiplier=1 are used for the first and second client respectively.

3. Run the Flower App#

With both the long-running server (SuperLink) and two clients (SuperNode) up and running, we can now run the actual Flower App:

flower-server-app server:app --insecure