¡El Día de la Comunidad de ML es el 9 de noviembre! Únase a nosotros para recibir actualizaciones de TensorFlow, JAX, y más Más información

Evalúe los riesgos de privacidad con el Informe de privacidad de TensorFlow

Ver en TensorFlow.org Ejecutar en Google Colab Ver fuente en GitHub Descargar cuaderno

Visión general

En este laboratorio de código, entrenará un modelo de clasificación de imágenes simple en el conjunto de datos CIFAR10 y luego usará el "ataque de inferencia de membresía" contra este modelo para evaluar si el atacante puede "adivinar" si una muestra en particular estaba presente en el conjunto de entrenamiento. . Utilizará el Informe de privacidad de TF para visualizar los resultados de varios modelos y puntos de control de modelos.

Configuración

import numpy as np
from typing import Tuple
from scipy import special
from sklearn import metrics

import tensorflow as tf

import tensorflow_datasets as tfds

# Set verbosity.
tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.ERROR)
from sklearn.exceptions import ConvergenceWarning

import warnings
warnings.simplefilter(action="ignore", category=ConvergenceWarning)
warnings.simplefilter(action="ignore", category=FutureWarning)

Instale TensorFlow Privacy.

pip install tensorflow_privacy
from tensorflow_privacy.privacy.privacy_tests.membership_inference_attack import membership_inference_attack as mia
from tensorflow_privacy.privacy.privacy_tests.membership_inference_attack.data_structures import AttackInputData
from tensorflow_privacy.privacy.privacy_tests.membership_inference_attack.data_structures import AttackResultsCollection
from tensorflow_privacy.privacy.privacy_tests.membership_inference_attack.data_structures import AttackType
from tensorflow_privacy.privacy.privacy_tests.membership_inference_attack.data_structures import PrivacyMetric
from tensorflow_privacy.privacy.privacy_tests.membership_inference_attack.data_structures import PrivacyReportMetadata
from tensorflow_privacy.privacy.privacy_tests.membership_inference_attack.data_structures import SlicingSpec
from tensorflow_privacy.privacy.privacy_tests.membership_inference_attack import privacy_report
import tensorflow_privacy

Entrene dos modelos, con métricas de privacidad

En esta sección se entrena un par de keras.Model clasificadores en la CIFAR-10 conjunto de datos. Durante el proceso de capacitación, recopila métricas de privacidad, que se utilizarán para generar informes en la sección bext.

El primer paso es definir algunos hiperparámetros:

dataset = 'cifar10'
num_classes = 10
activation = 'relu'
num_conv = 3

batch_size=50
epochs_per_report = 2
total_epochs = 50

lr = 0.001

A continuación, cargue el conjunto de datos. No hay nada específico de privacidad en este código.

print('Loading the dataset.')
train_ds = tfds.as_numpy(
    tfds.load(dataset, split=tfds.Split.TRAIN, batch_size=-1))
test_ds = tfds.as_numpy(
    tfds.load(dataset, split=tfds.Split.TEST, batch_size=-1))
x_train = train_ds['image'].astype('float32') / 255.
y_train_indices = train_ds['label'][:, np.newaxis]
x_test = test_ds['image'].astype('float32') / 255.
y_test_indices = test_ds['label'][:, np.newaxis]

# Convert class vectors to binary class matrices.
y_train = tf.keras.utils.to_categorical(y_train_indices, num_classes)
y_test = tf.keras.utils.to_categorical(y_test_indices, num_classes)

input_shape = x_train.shape[1:]

assert x_train.shape[0] % batch_size == 0, "The tensorflow_privacy optimizer doesn't handle partial batches"
Loading the dataset.

A continuación, defina una función para construir los modelos.

def small_cnn(input_shape: Tuple[int],
              num_classes: int,
              num_conv: int,
              activation: str = 'relu') -> tf.keras.models.Sequential:
  """Setup a small CNN for image classification.

  Args:
    input_shape: Integer tuple for the shape of the images.
    num_classes: Number of prediction classes.
    num_conv: Number of convolutional layers.
    activation: The activation function to use for conv and dense layers.

  Returns:
    The Keras model.
  """
  model = tf.keras.models.Sequential()
  model.add(tf.keras.layers.Input(shape=input_shape))

  # Conv layers
  for _ in range(num_conv):
    model.add(tf.keras.layers.Conv2D(32, (3, 3), activation=activation))
    model.add(tf.keras.layers.MaxPooling2D())

  model.add(tf.keras.layers.Flatten())
  model.add(tf.keras.layers.Dense(64, activation=activation))
  model.add(tf.keras.layers.Dense(num_classes))

  model.compile(
    loss=tf.keras.losses.CategoricalCrossentropy(from_logits=True),
    optimizer=tf.keras.optimizers.Adam(learning_rate=lr),
    metrics=['accuracy'])

  return model

Construya dos modelos CNN de tres capas usando esa función.

Configurar el primero en utilizar un optimizador básica SGD, un segundo para utilizar un optimizador de forma diferencial privada ( tf_privacy.DPKerasAdamOptimizer ), para que pueda comparar los resultados.

model_2layers = small_cnn(
    input_shape, num_classes, num_conv=2, activation=activation)
model_3layers = small_cnn(
    input_shape, num_classes, num_conv=3, activation=activation)

Definir una devolución de llamada para recopilar métricas de privacidad

A continuación, defina una keras.callbacks.Callback para funcionar periorically algunos ataques contra la privacidad del modelo, y registra los resultados.

Los Keras fit método llamará al on_epoch_end método después de cada época de entrenamiento. El n argumento es el número época (basado en 0).

Se podría aplicar este procedimiento al escribir un bucle que se llama repetidamente Model.fit(..., epochs=epochs_per_report) y se ejecuta el código de ataque. La devolución de llamada se usa aquí solo porque proporciona una separación clara entre la lógica de entrenamiento y la lógica de evaluación de la privacidad.

class PrivacyMetrics(tf.keras.callbacks.Callback):
  def __init__(self, epochs_per_report, model_name):
    self.epochs_per_report = epochs_per_report
    self.model_name = model_name
    self.attack_results = []

  def on_epoch_end(self, epoch, logs=None):
    epoch = epoch+1

    if epoch % self.epochs_per_report != 0:
      return

    print(f'\nRunning privacy report for epoch: {epoch}\n')

    logits_train = self.model.predict(x_train, batch_size=batch_size)
    logits_test = self.model.predict(x_test, batch_size=batch_size)

    prob_train = special.softmax(logits_train, axis=1)
    prob_test = special.softmax(logits_test, axis=1)

    # Add metadata to generate a privacy report.
    privacy_report_metadata = PrivacyReportMetadata(
        # Show the validation accuracy on the plot
        # It's what you send to train_accuracy that gets plotted.
        accuracy_train=logs['val_accuracy'], 
        accuracy_test=logs['val_accuracy'],
        epoch_num=epoch,
        model_variant_label=self.model_name)

    attack_results = mia.run_attacks(
        AttackInputData(
            labels_train=y_train_indices[:, 0],
            labels_test=y_test_indices[:, 0],
            probs_train=prob_train,
            probs_test=prob_test),
        SlicingSpec(entire_dataset=True, by_class=True),
        attack_types=(AttackType.THRESHOLD_ATTACK,
                      AttackType.LOGISTIC_REGRESSION),
        privacy_report_metadata=privacy_report_metadata)

    self.attack_results.append(attack_results)

Entrena a los modelos

El siguiente bloque de código entrena los dos modelos. El all_reports lista se utiliza para recoger todos los resultados de todas las carreras de entrenamiento de los modelos. Los informes individuales etiquetados comunicaba con el model_name , así que no hay confusión acerca de cuál es el modelo genera la cual informe.

all_reports = []
callback = PrivacyMetrics(epochs_per_report, "2 Layers")
history = model_2layers.fit(
      x_train,
      y_train,
      batch_size=batch_size,
      epochs=total_epochs,
      validation_data=(x_test, y_test),
      callbacks=[callback],
      shuffle=True)

all_reports.extend(callback.attack_results)
Epoch 1/50
1000/1000 [==============================] - 13s 4ms/step - loss: 1.5146 - accuracy: 0.4573 - val_loss: 1.2374 - val_accuracy: 0.5660
Epoch 2/50
1000/1000 [==============================] - 3s 3ms/step - loss: 1.1933 - accuracy: 0.5811 - val_loss: 1.1873 - val_accuracy: 0.5851

Running privacy report for epoch: 2

Epoch 3/50
1000/1000 [==============================] - 3s 3ms/step - loss: 1.0694 - accuracy: 0.6246 - val_loss: 1.0526 - val_accuracy: 0.6310
Epoch 4/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.9911 - accuracy: 0.6548 - val_loss: 0.9906 - val_accuracy: 0.6549

Running privacy report for epoch: 4

Epoch 5/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.9348 - accuracy: 0.6743 - val_loss: 0.9712 - val_accuracy: 0.6617
Epoch 6/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.8881 - accuracy: 0.6912 - val_loss: 0.9595 - val_accuracy: 0.6671

Running privacy report for epoch: 6

Epoch 7/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.8495 - accuracy: 0.7024 - val_loss: 0.9574 - val_accuracy: 0.6684
Epoch 8/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.8147 - accuracy: 0.7161 - val_loss: 0.9397 - val_accuracy: 0.6740

Running privacy report for epoch: 8

Epoch 9/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.7820 - accuracy: 0.7263 - val_loss: 0.9325 - val_accuracy: 0.6837
Epoch 10/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.7533 - accuracy: 0.7362 - val_loss: 0.9431 - val_accuracy: 0.6843

Running privacy report for epoch: 10

Epoch 11/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.7169 - accuracy: 0.7477 - val_loss: 0.9310 - val_accuracy: 0.6795
Epoch 12/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.6892 - accuracy: 0.7569 - val_loss: 0.9043 - val_accuracy: 0.6975

Running privacy report for epoch: 12

Epoch 13/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.6677 - accuracy: 0.7663 - val_loss: 0.9401 - val_accuracy: 0.6796
Epoch 14/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.6401 - accuracy: 0.7741 - val_loss: 0.9464 - val_accuracy: 0.6880

Running privacy report for epoch: 14

Epoch 15/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.6177 - accuracy: 0.7821 - val_loss: 0.9359 - val_accuracy: 0.6930
Epoch 16/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5978 - accuracy: 0.7913 - val_loss: 0.9634 - val_accuracy: 0.6896

Running privacy report for epoch: 16

Epoch 17/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5745 - accuracy: 0.7973 - val_loss: 0.9941 - val_accuracy: 0.6932
Epoch 18/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5553 - accuracy: 0.8036 - val_loss: 0.9790 - val_accuracy: 0.6974

Running privacy report for epoch: 18

Epoch 19/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5376 - accuracy: 0.8103 - val_loss: 0.9989 - val_accuracy: 0.6907
Epoch 20/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5152 - accuracy: 0.8192 - val_loss: 1.0245 - val_accuracy: 0.6878

Running privacy report for epoch: 20

Epoch 21/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5048 - accuracy: 0.8208 - val_loss: 1.0223 - val_accuracy: 0.6852
Epoch 22/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.4847 - accuracy: 0.8284 - val_loss: 1.0498 - val_accuracy: 0.6866

Running privacy report for epoch: 22

Epoch 23/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.4722 - accuracy: 0.8325 - val_loss: 1.0610 - val_accuracy: 0.6899
Epoch 24/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.4562 - accuracy: 0.8387 - val_loss: 1.0973 - val_accuracy: 0.6771

Running privacy report for epoch: 24

Epoch 25/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.4392 - accuracy: 0.8447 - val_loss: 1.1141 - val_accuracy: 0.6865
Epoch 26/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.4269 - accuracy: 0.8485 - val_loss: 1.1928 - val_accuracy: 0.6771

Running privacy report for epoch: 26

Epoch 27/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.4135 - accuracy: 0.8533 - val_loss: 1.1945 - val_accuracy: 0.6758
Epoch 28/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.4053 - accuracy: 0.8569 - val_loss: 1.2244 - val_accuracy: 0.6716

Running privacy report for epoch: 28

Epoch 29/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.3880 - accuracy: 0.8611 - val_loss: 1.2362 - val_accuracy: 0.6789
Epoch 30/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.3805 - accuracy: 0.8630 - val_loss: 1.2815 - val_accuracy: 0.6805

Running privacy report for epoch: 30

Epoch 31/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.3756 - accuracy: 0.8656 - val_loss: 1.2973 - val_accuracy: 0.6762
Epoch 32/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.3565 - accuracy: 0.8719 - val_loss: 1.3022 - val_accuracy: 0.6810

Running privacy report for epoch: 32

Epoch 33/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.3494 - accuracy: 0.8749 - val_loss: 1.3248 - val_accuracy: 0.6756
Epoch 34/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.3371 - accuracy: 0.8790 - val_loss: 1.3941 - val_accuracy: 0.6806

Running privacy report for epoch: 34

Epoch 35/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.3248 - accuracy: 0.8839 - val_loss: 1.4391 - val_accuracy: 0.6666
Epoch 36/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.3233 - accuracy: 0.8833 - val_loss: 1.5060 - val_accuracy: 0.6692

Running privacy report for epoch: 36

Epoch 37/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.3109 - accuracy: 0.8882 - val_loss: 1.4624 - val_accuracy: 0.6724
Epoch 38/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.3057 - accuracy: 0.8900 - val_loss: 1.5133 - val_accuracy: 0.6644

Running privacy report for epoch: 38

Epoch 39/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.2929 - accuracy: 0.8949 - val_loss: 1.5465 - val_accuracy: 0.6618
Epoch 40/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.2868 - accuracy: 0.8970 - val_loss: 1.5882 - val_accuracy: 0.6696

Running privacy report for epoch: 40

Epoch 41/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.2778 - accuracy: 0.8982 - val_loss: 1.6317 - val_accuracy: 0.6713
Epoch 42/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.2782 - accuracy: 0.8999 - val_loss: 1.6993 - val_accuracy: 0.6630

Running privacy report for epoch: 42

Epoch 43/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.2675 - accuracy: 0.9039 - val_loss: 1.7294 - val_accuracy: 0.6645
Epoch 44/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.2587 - accuracy: 0.9068 - val_loss: 1.7614 - val_accuracy: 0.6561

Running privacy report for epoch: 44

Epoch 45/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.2528 - accuracy: 0.9076 - val_loss: 1.7835 - val_accuracy: 0.6564
Epoch 46/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.2410 - accuracy: 0.9129 - val_loss: 1.8550 - val_accuracy: 0.6648

Running privacy report for epoch: 46

Epoch 47/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.2409 - accuracy: 0.9106 - val_loss: 1.8705 - val_accuracy: 0.6572
Epoch 48/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.2328 - accuracy: 0.9146 - val_loss: 1.9110 - val_accuracy: 0.6593

Running privacy report for epoch: 48

Epoch 49/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.2299 - accuracy: 0.9164 - val_loss: 1.9468 - val_accuracy: 0.6634
Epoch 50/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.2250 - accuracy: 0.9178 - val_loss: 2.0154 - val_accuracy: 0.6610

Running privacy report for epoch: 50
callback = PrivacyMetrics(epochs_per_report, "3 Layers")
history = model_3layers.fit(
      x_train,
      y_train,
      batch_size=batch_size,
      epochs=total_epochs,
      validation_data=(x_test, y_test),
      callbacks=[callback],
      shuffle=True)

all_reports.extend(callback.attack_results)
Epoch 1/50
1000/1000 [==============================] - 4s 4ms/step - loss: 1.6838 - accuracy: 0.3772 - val_loss: 1.4805 - val_accuracy: 0.4552
Epoch 2/50
1000/1000 [==============================] - 3s 3ms/step - loss: 1.3938 - accuracy: 0.4969 - val_loss: 1.3291 - val_accuracy: 0.5276

Running privacy report for epoch: 2

Epoch 3/50
1000/1000 [==============================] - 3s 3ms/step - loss: 1.2564 - accuracy: 0.5510 - val_loss: 1.2313 - val_accuracy: 0.5627
Epoch 4/50
1000/1000 [==============================] - 3s 3ms/step - loss: 1.1610 - accuracy: 0.5884 - val_loss: 1.1251 - val_accuracy: 0.6039

Running privacy report for epoch: 4

Epoch 5/50
1000/1000 [==============================] - 3s 3ms/step - loss: 1.1034 - accuracy: 0.6105 - val_loss: 1.1168 - val_accuracy: 0.6063
Epoch 6/50
1000/1000 [==============================] - 3s 3ms/step - loss: 1.0476 - accuracy: 0.6319 - val_loss: 1.0716 - val_accuracy: 0.6248

Running privacy report for epoch: 6

Epoch 7/50
1000/1000 [==============================] - 3s 3ms/step - loss: 1.0107 - accuracy: 0.6461 - val_loss: 1.0264 - val_accuracy: 0.6407
Epoch 8/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.9731 - accuracy: 0.6597 - val_loss: 1.0216 - val_accuracy: 0.6447

Running privacy report for epoch: 8

Epoch 9/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.9437 - accuracy: 0.6712 - val_loss: 1.0016 - val_accuracy: 0.6467
Epoch 10/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.9191 - accuracy: 0.6790 - val_loss: 0.9845 - val_accuracy: 0.6553

Running privacy report for epoch: 10

Epoch 11/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.8923 - accuracy: 0.6877 - val_loss: 0.9560 - val_accuracy: 0.6670
Epoch 12/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.8722 - accuracy: 0.6959 - val_loss: 0.9518 - val_accuracy: 0.6686

Running privacy report for epoch: 12

Epoch 13/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.8495 - accuracy: 0.7029 - val_loss: 0.9427 - val_accuracy: 0.6787
Epoch 14/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.8305 - accuracy: 0.7116 - val_loss: 0.9247 - val_accuracy: 0.6814

Running privacy report for epoch: 14

Epoch 15/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.8164 - accuracy: 0.7157 - val_loss: 0.9263 - val_accuracy: 0.6797
Epoch 16/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.7973 - accuracy: 0.7220 - val_loss: 0.9151 - val_accuracy: 0.6850

Running privacy report for epoch: 16

Epoch 17/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.7830 - accuracy: 0.7277 - val_loss: 0.9139 - val_accuracy: 0.6842
Epoch 18/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.7704 - accuracy: 0.7294 - val_loss: 0.9384 - val_accuracy: 0.6774

Running privacy report for epoch: 18

Epoch 19/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.7539 - accuracy: 0.7366 - val_loss: 0.9508 - val_accuracy: 0.6761
Epoch 20/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.7445 - accuracy: 0.7412 - val_loss: 0.9108 - val_accuracy: 0.6908

Running privacy report for epoch: 20

Epoch 21/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.7343 - accuracy: 0.7418 - val_loss: 0.9161 - val_accuracy: 0.6855
Epoch 22/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.7213 - accuracy: 0.7458 - val_loss: 0.9754 - val_accuracy: 0.6724

Running privacy report for epoch: 22

Epoch 23/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.7133 - accuracy: 0.7487 - val_loss: 0.8936 - val_accuracy: 0.6984
Epoch 24/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.7072 - accuracy: 0.7504 - val_loss: 0.8872 - val_accuracy: 0.7002

Running privacy report for epoch: 24

Epoch 25/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.6932 - accuracy: 0.7570 - val_loss: 0.9732 - val_accuracy: 0.6769
Epoch 26/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.6883 - accuracy: 0.7578 - val_loss: 0.9332 - val_accuracy: 0.6798

Running privacy report for epoch: 26

Epoch 27/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.6766 - accuracy: 0.7614 - val_loss: 0.9069 - val_accuracy: 0.6998
Epoch 28/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.6656 - accuracy: 0.7662 - val_loss: 0.8879 - val_accuracy: 0.7011

Running privacy report for epoch: 28

Epoch 29/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.6594 - accuracy: 0.7674 - val_loss: 0.8988 - val_accuracy: 0.7037
Epoch 30/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.6499 - accuracy: 0.7700 - val_loss: 0.9086 - val_accuracy: 0.7001

Running privacy report for epoch: 30

Epoch 31/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.6420 - accuracy: 0.7746 - val_loss: 0.8985 - val_accuracy: 0.7034
Epoch 32/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.6354 - accuracy: 0.7742 - val_loss: 0.9089 - val_accuracy: 0.7018

Running privacy report for epoch: 32

Epoch 33/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.6293 - accuracy: 0.7759 - val_loss: 0.9258 - val_accuracy: 0.6947
Epoch 34/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.6192 - accuracy: 0.7851 - val_loss: 0.9326 - val_accuracy: 0.6976

Running privacy report for epoch: 34

Epoch 35/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.6157 - accuracy: 0.7831 - val_loss: 0.9240 - val_accuracy: 0.6973
Epoch 36/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.6063 - accuracy: 0.7853 - val_loss: 0.9504 - val_accuracy: 0.6971

Running privacy report for epoch: 36

Epoch 37/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.6036 - accuracy: 0.7867 - val_loss: 0.9025 - val_accuracy: 0.7094
Epoch 38/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5958 - accuracy: 0.7877 - val_loss: 0.9290 - val_accuracy: 0.6976

Running privacy report for epoch: 38

Epoch 39/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5900 - accuracy: 0.7919 - val_loss: 0.9379 - val_accuracy: 0.6963
Epoch 40/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5856 - accuracy: 0.7928 - val_loss: 0.9911 - val_accuracy: 0.6896

Running privacy report for epoch: 40

Epoch 41/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5772 - accuracy: 0.7944 - val_loss: 0.9093 - val_accuracy: 0.7059
Epoch 42/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5752 - accuracy: 0.7940 - val_loss: 0.9275 - val_accuracy: 0.7061

Running privacy report for epoch: 42

Epoch 43/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5645 - accuracy: 0.7998 - val_loss: 0.9208 - val_accuracy: 0.7025
Epoch 44/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5632 - accuracy: 0.8000 - val_loss: 0.9746 - val_accuracy: 0.6976

Running privacy report for epoch: 44

Epoch 45/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5557 - accuracy: 0.8045 - val_loss: 0.9211 - val_accuracy: 0.7098
Epoch 46/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5469 - accuracy: 0.8073 - val_loss: 0.9357 - val_accuracy: 0.7055

Running privacy report for epoch: 46

Epoch 47/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5438 - accuracy: 0.8062 - val_loss: 0.9495 - val_accuracy: 0.7025
Epoch 48/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5437 - accuracy: 0.8069 - val_loss: 0.9509 - val_accuracy: 0.6994

Running privacy report for epoch: 48

Epoch 49/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5414 - accuracy: 0.8066 - val_loss: 0.9780 - val_accuracy: 0.6939
Epoch 50/50
1000/1000 [==============================] - 3s 3ms/step - loss: 0.5321 - accuracy: 0.8108 - val_loss: 1.0109 - val_accuracy: 0.6846

Running privacy report for epoch: 50

Parcelas de época

Puede visualizar cómo se producen los riesgos de privacidad a medida que entrena modelos probando el modelo periódicamente (por ejemplo, cada 5 épocas), puede elegir el punto en el tiempo con la mejor compensación de rendimiento / privacidad.

Utilizar el TF Privacidad módulo de afiliación Inferencia de ataque para generar AttackResults . Estos AttackResults consiguen combinarse en una AttackResultsCollection . El Informe TF privacidad está diseñada para analizar la proporcionada AttackResultsCollection .

results = AttackResultsCollection(all_reports)
privacy_metrics = (PrivacyMetric.AUC, PrivacyMetric.ATTACKER_ADVANTAGE)
epoch_plot = privacy_report.plot_by_epochs(
    results, privacy_metrics=privacy_metrics)

png

Vea que, como regla, la vulnerabilidad de la privacidad tiende a aumentar a medida que aumenta el número de épocas. Esto es cierto en todas las variantes del modelo, así como en los diferentes tipos de atacantes.

Los modelos de dos capas (con menos capas convolucionales) son generalmente más vulnerables que sus contrapartes del modelo de tres capas.

Ahora veamos cómo cambia el rendimiento del modelo con respecto al riesgo de privacidad.

Privacidad vs utilidad

privacy_metrics = (PrivacyMetric.AUC, PrivacyMetric.ATTACKER_ADVANTAGE)
utility_privacy_plot = privacy_report.plot_privacy_vs_accuracy(
    results, privacy_metrics=privacy_metrics)

for axis in utility_privacy_plot.axes:
  axis.set_xlabel('Validation accuracy')

png

Los modelos de tres capas (quizás debido a demasiados parámetros) solo logran una precisión de tren de 0,85. Los modelos de dos capas logran un rendimiento aproximadamente igual para ese nivel de riesgo de privacidad, pero continúan obteniendo una mejor precisión.

También puede ver cómo la línea para los modelos de dos capas se vuelve más pronunciada. Esto significa que las ganancias marginales adicionales en la precisión del tren se producen a expensas de grandes vulnerabilidades de privacidad.

Este es el final del tutorial. No dude en analizar sus propios resultados.