python/dp_auditorium/dp_auditorium/examples/run_mean_mechanism_example.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "K0EnDo__AXCC"
      },
      "source": [
        "\u003ctable class=\"tfo-notebook-buttons\" align=\"left\"\u003e\n",
        "  \u003ctd\u003e\n",
        "    \u003ca target=\"_blank\" href=\"https://colab.research.google.com/github/google/differential-privacy/blob/main/python/dp_auditorium/dp_auditorium/examples/run_mean_mechanism_example.ipynb\"\u003e\u003cimg src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" /\u003eRun in Google Colab\u003c/a\u003e\n",
        "  \u003c/td\u003e\n",
        "  \u003ctd\u003e\n",
        "    \u003ca target=\"_blank\" href=\"https://github.com/google/differential-privacy/blob/main/python/dp_auditorium/dp_auditorium/examples/run_mean_mechanism_example.ipynb\"\u003e\u003cimg src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" /\u003eView source on GitHub\u003c/a\u003e\n",
        "  \u003c/td\u003e\n",
        "\u003c/table\u003e\n",
        "\n",
        "\u003cbr\u003e\n",
        "\u003cbr\u003e\n",
        "\n",
        "Or see this example in a [Python file](https://github.com/google/differential-privacy/blob/main/python/dp_auditorium/dp_auditorium/examples/run_mean_mechanism_example.py)."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "cellView": "form",
        "id": "llOhiK3ruVWF"
      },
      "outputs": [],
      "source": [
        "#@title Install and import dp_auditorium and all necessary libraries.\n",
        "!pip install google-vizier equinox\n",
        "!git clone https://github.com/google/differential-privacy.git\n",
        "import sys\n",
        "sys.path.append('differential-privacy/python/dp_auditorium')\n",
        "\n",
        "from dp_auditorium import interfaces\n",
        "from dp_auditorium import privacy_test_runner\n",
        "from dp_auditorium.generators import vizier_dataset_generator\n",
        "from dp_auditorium.configs import dataset_generator_config\n",
        "from dp_auditorium.configs import privacy_property\n",
        "from dp_auditorium.configs import privacy_test_runner_config\n",
        "\n",
        "import numpy as np\n",
        "import dataclasses"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "dr5A5W7Aq2SO"
      },
      "outputs": [],
      "source": [
        "#@title Mean mechanism example\n",
        "\n",
        "from typing import Callable\n",
        "import time\n",
        "\n",
        "# https://github.com/google/differential-privacy/blob/main/python/dp_auditorium/dp_auditorium/examples/run_mean_mechanism_example.py\n",
        "def default_generator_factory(\n",
        "    config: dataset_generator_config.VizierDatasetGeneratorConfig,\n",
        ") -\u003e vizier_dataset_generator.VizierScalarDataAddRemoveGenerator:\n",
        "  return vizier_dataset_generator.VizierScalarDataAddRemoveGenerator(\n",
        "      config=config\n",
        "  )\n",
        "\n",
        "\n",
        "def mean_mechanism_report(\n",
        "    epsilon: float,\n",
        "    delta: float,\n",
        "    seed: int,\n",
        "    generator_factory: Callable[\n",
        "        [dataset_generator_config.VizierDatasetGeneratorConfig],\n",
        "        vizier_dataset_generator.VizierScalarDataAddRemoveGenerator,\n",
        "    ] = default_generator_factory,\n",
        ") -\u003e privacy_test_runner_config.PrivacyTestRunnerResults:\n",
        "  \"\"\"Runs the example code for a mean mechanism.\n",
        "\n",
        "  Args:\n",
        "    epsilon: standard approximate DP parmaeter.\n",
        "    delta: standard approximate DP parameter.\n",
        "    seed: seed to initialize the random number generator.\n",
        "    generator_factory: factory to create a generator; to be replaced in tests\n",
        "\n",
        "  Returns:\n",
        "    The result of the example code as PrivacyTestRunnerResults.\n",
        "  \"\"\"\n",
        "  rng = np.random.default_rng(seed=seed)\n",
        "  tf.random.set_seed(seed)\n",
        "\n",
        "  # Configuration for a non-private mean mechanism that uses the true number of\n",
        "  # points to calculate the average and the scale of the noise.\n",
        "  mech_config = mechanism_config.MeanMechanismConfig(\n",
        "      epsilon=epsilon,\n",
        "      delta=delta,\n",
        "      use_noised_counts_for_calculating_mean=False,\n",
        "      use_noised_counts_for_calculating_noise_scale=False,\n",
        "      min_value=0.0,\n",
        "      max_value=1.0,\n",
        "  )\n",
        "  # Initialize the mechanism.\n",
        "  mechanism = mean.MeanMechanism(mech_config, rng)\n",
        "\n",
        "  # Configuration for a Hockey-Stick property tester. Given arrays s1 and s2\n",
        "  # with samples two distributions it will estimate the hockey-stick divergence\n",
        "  # from the underlying distributions. It checks if the divergence is bounded by\n",
        "  # delta.\n",
        "  tester_config = property_tester_config.HockeyStickPropertyTesterConfig(\n",
        "      training_config=hockey_stick_tester.make_default_hs_training_config(),\n",
        "      approximate_dp=privacy_property.ApproximateDp(\n",
        "          epsilon=epsilon,\n",
        "          delta=delta,\n",
        "      ),\n",
        "  )\n",
        "  # Initialize a classifier model for the Hockey-Stick property tester.\n",
        "  # This classifier will learn to distinguish between samples of the mechanism\n",
        "  # on adjacent datasets. Its accuracy level should be controlled by the privacy\n",
        "  # guarantee.\n",
        "  base_model = hockey_stick_tester.make_default_hs_base_model()\n",
        "  # Initialize a property tester.\n",
        "  property_tester = hockey_stick_tester.HockeyStickPropertyTester(\n",
        "      config=tester_config,\n",
        "      base_model=base_model,\n",
        "  )\n",
        "\n",
        "  # Configuration for dataset generator. It generates neighboring datasets under\n",
        "  # the add/remove definition. Unique study name prevents using cached results\n",
        "  # from previous runs.\n",
        "  generator_config = dataset_generator_config.VizierDatasetGeneratorConfig(\n",
        "      study_name=str(time.time()),\n",
        "      study_owner=\"owner\",\n",
        "      num_vizier_parameters=2,\n",
        "      data_type=dataset_generator_config.DataType.DATA_TYPE_FLOAT,\n",
        "      min_value=-1.0,\n",
        "      max_value=1.0,\n",
        "      search_algorithm=\"RANDOM_SEARCH\",\n",
        "      metric_name=\"hockey_stick_divergence\",\n",
        "  )\n",
        "  # Initialize the dataset generator.\n",
        "  dataset_generator = generator_factory(generator_config)\n",
        "\n",
        "  # Configuration for the test runner.\n",
        "  # The test runner coordinates how the test is evaluated. It receives a\n",
        "  # dataset generator, a property tester and a configuration (see base class for\n",
        "  # details on these parameters), and runs privacy tests using the property\n",
        "  # tester on datasets generated by the dataset generator.\n",
        "  test_runner_config = privacy_test_runner_config.PrivacyTestRunnerConfig(\n",
        "      property_tester=privacy_test_runner_config.PropertyTester.HOCKEY_STICK_TESTER,\n",
        "      max_num_trials=10,\n",
        "      failure_probability=0.05,\n",
        "      num_samples=10_000,\n",
        "      # Apply a hyperbolic tangent function to the output of the mechanism\n",
        "      post_processing=privacy_test_runner_config.PostProcessing.TANH,\n",
        "  )\n",
        "  # Initialize the test runner.\n",
        "  test_runner = privacy_test_runner.PrivacyTestRunner(\n",
        "      config=test_runner_config,\n",
        "      dataset_generator=dataset_generator,\n",
        "      property_tester=property_tester,\n",
        "  )\n",
        "\n",
        "  return test_runner.test_privacy(mechanism, \"non-private-mean-mechanism\")\n",
        "\n",
        "\n",
        "EPSILON = 1.0\n",
        "DELTA = 1e-5\n",
        "SEED = 1\n",
        "\n",
        "# The results indicate whether a privacy violation was identified within the\n",
        "# designated number of trials defined in the configuration. In the absence of a\n",
        "# violation, a message is returned indicating that the limit of the number of\n",
        "# trials has been reached. For reference, all computed divergences across all\n",
        "# trials are also reported.\n",
        "results = mean_mechanism_report(EPSILON, DELTA, SEED)\n",
        "print(f\" \\nResults: \\n{results}\")"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "private_outputs": true,
      "provenance": [
        {
          "file_id": "1QyFD_doucyHewiRMtxGvFxNrFlgbCqQa",
          "timestamp": 1708693099970
        },
        {
          "file_id": "1pBgTlH19OwJ3diUYf3m3QaZcVNQGeB8B",
          "timestamp": 1708692052606
        }
      ]
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}