 Voir sur TensorFlow.org |  Exécuter dans Google Colab |  Voir la source sur GitHub |  Télécharger le cahier |
Aperçu
Dans ce laboratoire de programmation, vous entraînerez un modèle de classification d'images simple sur l'ensemble de données CIFAR10, puis utiliserez « l'attaque par inférence d'appartenance » contre ce modèle pour évaluer si l'attaquant est capable de « deviner » si un échantillon particulier était présent dans l'ensemble d'entraînement . Vous utiliserez le rapport de confidentialité TF pour visualiser les résultats de plusieurs modèles et points de contrôle de modèle.
Installer
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)
Installez 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
Former deux modèles, avec des métriques de confidentialité
Cette section forme une paire de keras.Model classificateurs sur l' CIFAR-10 ensemble de données. Au cours du processus de formation, il collecte des mesures de confidentialité, qui seront utilisées pour générer des rapports dans la section suivante.
La première étape consiste à définir quelques hyperparamètres :
dataset = 'cifar10'
num_classes = 10
activation = 'relu'
num_conv = 3
batch_size=50
epochs_per_report = 2
total_epochs = 50
lr = 0.001
Ensuite, chargez l'ensemble de données. Il n'y a rien de spécifique à la confidentialité dans ce code.
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.
Ensuite, définissez une fonction pour construire les modèles.
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
Construisez deux modèles CNN à trois couches à l'aide de cette fonction.
Configurez le premier à utiliser un optimiseur de SGD de base, un second à utiliser un optimiseur privé différentiellement ( tf_privacy.DPKerasAdamOptimizer ), afin que vous puissiez comparer les résultats.
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)
Définir un rappel pour collecter des métriques de confidentialité
Suivant définir un keras.callbacks.Callback pour exécuter periorically des attaques de la vie privée contre le modèle, et consigner les résultats.
Les keras fit la méthode appellera la on_epoch_end méthode après chaque époque de formation. Le n argument est le (0-based) Numéro d'époque.
Vous pouvez mettre en œuvre cette procédure en écrivant une boucle qui appelle à plusieurs reprises Model.fit(..., epochs=epochs_per_report) et exécute le code d'attaque. Le rappel est utilisé ici simplement parce qu'il sépare clairement la logique d'apprentissage et la logique d'évaluation de la confidentialité.
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)
Former les modèles
Le bloc de code suivant entraîne les deux modèles. La all_reports liste est utilisée pour recueillir tous les résultats de tous les entraînements les modèles. Les rapports individuels sont marqués witht le model_name , donc il n'y a pas de confusion sur le modèle généré quel rapport.
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
Parcelles d'époque
Vous pouvez visualiser comment les risques de confidentialité surviennent lorsque vous entraînez des modèles en sondant le modèle périodiquement (par exemple toutes les 5 époques), vous pouvez choisir le moment avec le meilleur compromis performances / confidentialité.
Utilisez l'adhésion de confidentialité TF Inference Module d' attaque pour générer AttackResults . Ces AttackResults sont combinées dans un AttackResultsCollection . Le rapport de confidentialité TF est conçu pour analyser la condition AttackResultsCollection .
results = AttackResultsCollection(all_reports)
privacy_metrics = (PrivacyMetric.AUC, PrivacyMetric.ATTACKER_ADVANTAGE)
epoch_plot = privacy_report.plot_by_epochs(
results, privacy_metrics=privacy_metrics)
Voyez qu'en règle générale, la vulnérabilité de la vie privée a tendance à augmenter à mesure que le nombre d'époques augmente. Cela est vrai pour toutes les variantes de modèles ainsi que pour différents types d'attaquants.
Les modèles à deux couches (avec moins de couches convolutives) sont généralement plus vulnérables que leurs homologues des modèles à trois couches.
Voyons maintenant comment les performances du modèle changent en ce qui concerne le risque de confidentialité.
Confidentialité vs utilitaire
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')
Les modèles à trois couches (peut-être en raison d'un trop grand nombre de paramètres) n'atteignent qu'une précision de train de 0,85. Les modèles à deux couches atteignent des performances à peu près égales pour ce niveau de risque de confidentialité, mais ils continuent d'obtenir une meilleure précision.
Vous pouvez également voir comment la ligne des modèles à deux couches devient plus raide. Cela signifie que des gains marginaux supplémentaires en termes de précision des trains se font au détriment de vastes vulnérabilités en matière de confidentialité.
C'est la fin du tutoriel. N'hésitez pas à analyser vos propres résultats.