# TODO(b/181782485): Switch to the main book for launch - /responsible_ai/_book.yaml
book_path: /responsible_ai/privacy/_book.yaml
project_path: /responsible_ai/_project.yaml
title: TensorFlow Privacy
description: >
 Overview of TensorFlow Privacy library.
landing_page:
  nav: left
  custom_css_path: /site-assets/css/style.css
  rows:
  - heading: Privacy in Machine Learning
    items:
    - classname: devsite-landing-row-50
      description: >
        <p>
        Preventing ML models from exposing potentially sensitive information is a critical part of
        using AI responsibly. To that end, <i>differentially private stochastic gradient descent
        (DP-SGD)</i> is a modification to the standard stochastic gradient descent (SGD) algorithm
        in machine learning. </p>
        <p>Models trained with DP-SGD have provable differential privacy (DP)
        guarantees, mitigating the risk of exposing sensitive training data. Intuitively, a model
        trained with differential privacy should not be affected by any single training example in
        its data set. DP-SGD techniques can also be used in federated learning to provide user-level
        differential privacy. You can learn more about differentially private deep learning in <a
        href="https://arxiv.org/pdf/1607.00133.pdf">the original paper</a>.
        </p>

    - code_block: |
        <pre class = "prettyprint">
        import tensorflow as tf
        from tensorflow_privacy.privacy.optimizers import dp_optimizer_keras

        # Select your differentially private optimizer
        optimizer = tensorflow_privacy.DPKerasSGDOptimizer(
            l2_norm_clip=l2_norm_clip,
            noise_multiplier=noise_multiplier,
            num_microbatches=num_microbatches,
            learning_rate=learning_rate)

        # Select your loss function
        loss = tf.keras.losses.CategoricalCrossentropy(
            from_logits=True, reduction=tf.losses.Reduction.NONE)

        # Compile your model
        model.compile(optimizer=optimizer, loss=loss, metrics=['accuracy'])

        # Fit your model
        model.fit(train_data, train_labels,
          epochs=epochs,
          validation_data=(test_data, test_labels),
          batch_size=batch_size)
          </pre>

  - classname: devsite-landing-row-100
  - heading: TensorFlow Privacy
    options:
    - description-100
    items:
    - classname: devsite-landing-row-100
      description: >
        <p>Tensorflow Privacy (TF Privacy) is an open source library developed by teams in Google
        Research. The library includes implementations of commonly used TensorFlow Optimizers for
        training ML models with DP. The goal is to enable ML practitioners using standard Tensorflow
        APIs to train privacy-preserving models by changing only a few lines of code.</p>
        <p> The differentially private Optimizers can be used in conjunction with high-level APIs
        that use the Optimizer class, especially Keras. Additionally, you can find differentially
        private implementations of some Keras models. All of the Optimizers and models can be found
        in the <a href="./privacy/api">API Documentation</a>.</p>

  - classname: devsite-landing-row-cards
    items:
    - heading: "Introducing TensorFlow Privacy"
      image_path: /resources/images/tf-logo-card-16x9.png
      path: https://blog.tensorflow.org/2019/03/introducing-tensorflow-privacy-learning.html
      buttons:
      - label: "Read on TensorFlow blog"
        path: https://blog.tensorflow.org/2019/03/introducing-tensorflow-privacy-learning.html
    - heading: "TensorFlow Privacy at TF Dev Summit 2020"
      youtube_id: UEECKh6PLhI
      buttons:
      - label: Watch the video
        path: https://www.youtube.com/watch?v=UEECKh6PLhI
    - heading: "TensorFlow Privacy on GitHub"
      image_path: /resources/images/github-card-16x9.png
      path: https://github.com/tensorflow/privacy
      buttons:
      - label: "View on GitHub"
        path: https://github.com/tensorflow/privacy