Nie można uruchomić atak Карлини i Wagnera z pomocą foolbox w modelu тензорного przepływu

Question 1

Używam najnowszej wersji foolbox (3.3.1) i mój kod po prostu ładuje CNN RESNET-50, dodaje kilka warstw dla wysłanej aplikacji edukacyjnych i ładuje wagi w następujący sposób.

from numpy.core.records import array
import tensorflow as tf
from keras.applications.resnet50 import ResNet50, preprocess_input
from tensorflow.keras.layers import Dense, Dropout, Flatten
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input
import cv2
import os
import numpy as np
import foolbox as FB
from sklearn.metrics import accuracy_score
from scipy.spatial.distance import cityblock
from sklearn.metrics import plot_confusion_matrix
from sklearn.metrics import confusion_matrix
from PIL import Image
import foolbox as FB
import math
from foolbox.criteria import Misclassification

#load model
num_classes = 12

#Load model and prepare it for testing
print("Step 1: Load model and weights")
baseModel = ResNet50(weights=None, include_top=False, input_tensor=Input(shape=(224, 224, 3)))
headModel = baseModel.output
headModel = Flatten(name="flatten")(headModel)
headModel = Dense(512, activation="relu")(headModel)
headModel = Dropout(0.5)(headModel)
headModel = Dense(num_classes, activation="softmax")(headModel)
model = Model(inputs=baseModel.input, outputs=headModel)
model.load_weights("RESNET-50/weights/train1-test1.h5")

print("Step 2: prepare testing data")
#features is a set of (1200,10,224,224,3) images
features=np.load("features.npy")
labels=np.load("labels.npy")

Teraz chciałbym go atakować za pomocą ataku foolbox 3.3.1 Карлини i Wagnera, to jak przesyłam model dla foolbox

#Lets test the foolbox model
bounds = (0, 1)
fmodel = fb.TensorFlowModel(model, bounds=bounds)

Mój zestaw danych jest podzielona na 10 zdjęć na dokument, będę atakować te 10 zdjęć za pomocą rozmiar pakietu 10 do foolbox za pomocą ataku Карлини i Wagnera

#for each i, I have 10 images
for i in range(0, features.shape[0]):

    print("document "+str(i))

    #Receive current values
    #This is a batch of (10,224,224,3) images
    features_to_test=features[i,:]
    #Get their labels
    labels_to_test=labels[i,:]

    ######################ATTACK IN THE NORMALIZED DOMAIN###########################  
    #lets do the attack
    #We use an interval of epsilons

    epsilons = np.linspace(0.01, 1, num=2)
    attack = fb.attacks.L2CarliniWagnerAttack(fmodel)
    adversarials = attack(features_to_test, labels_to_test, criterion=Misclassification(labels=labels_to_test), epsilons=epsilons)

Jednak za każdym razem, gdy uruchamiam kod, mi, zwracany jest błąd

Traceback (most recent call last):
File "test_carlini_wagner.py", line 161, in <module>
adversarials = attack(features_to_test, labels_to_test, 
criterion=Misclassification(labels=labels_to_test), epsilons=epsilons)
File "/usr/local/lib/python3.8/dist-packages/foolbox/attacks/base.py", line 410, in 
__call__
xp = self.run(model, x, criterion, early_stop=early_stop, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/foolbox/attacks/carlini_wagner.py", line 100, in run
bounds = model.bounds
AttributeError: 'tensorflow.python.framework.ops.EagerTensor' object has no attribute 
'bounds'

W co musi być błąd? źle pobierania swój model? czy muszę dodać nowe opcje dla spowodowane przez atak? jak już wspomniano wcześniej, jestem w foolbox 3.3.1.

Question 2

Myślę, że może pomylili ustawienia L2CarliniWagnerAttack. Oto uproszczony roboczy przykład z fałszywymi danymi:

import tensorflow as tf
import numpy as np

from tensorflow.keras.applications.resnet50 import ResNet50, preprocess_input
from tensorflow.keras.layers import Dense, Dropout, Flatten
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input
from sklearn.metrics import accuracy_score
from scipy.spatial.distance import cityblock
from sklearn.metrics import plot_confusion_matrix
from sklearn.metrics import confusion_matrix
from foolbox import TensorFlowModel
from foolbox.criteria import Misclassification
from foolbox.attacks import L2CarliniWagnerAttack

num_classes = 12

print("Step 1: Load model and weights")
baseModel = ResNet50(weights=None, include_top=False, input_tensor=Input(shape=(224, 224, 3)))
headModel = baseModel.output
headModel = Flatten(name="flatten")(headModel)
headModel = Dense(512, activation="relu")(headModel)
headModel = Dropout(0.5)(headModel)
headModel = Dense(num_classes, activation="softmax")(headModel)
model = Model(inputs=baseModel.input, outputs=headModel)

bounds = (0, 1)
fmodel = TensorFlowModel(model, bounds=bounds)
images, labels = tf.random.normal((64, 10, 224, 224, 3)), tf.random.uniform((64, 10,), maxval=13, dtype=tf.int32)

for i in range(0, images.shape[0]):

    print("document "+str(i))
    features_to_test=images[i,:]
    labels_to_test=labels[i,:]

    epsilons = np.linspace(0.01, 1, num=2)
    attack = L2CarliniWagnerAttack()
    adversarials = attack(fmodel, features_to_test, criterion=Misclassification(labels_to_test), epsilons=epsilons)

Step 1: Load model and weights
document 0
document 1
document 2
document 3
document 4
document 5
document 6
...

AloneTogether · Answer 1 · 2021-11-23T12:13:46

Myślę, że może pomylili ustawienia L2CarliniWagnerAttack. Oto uproszczony roboczy przykład z fałszywymi danymi:

import tensorflow as tf
import numpy as np

from tensorflow.keras.applications.resnet50 import ResNet50, preprocess_input
from tensorflow.keras.layers import Dense, Dropout, Flatten
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input
from sklearn.metrics import accuracy_score
from scipy.spatial.distance import cityblock
from sklearn.metrics import plot_confusion_matrix
from sklearn.metrics import confusion_matrix
from foolbox import TensorFlowModel
from foolbox.criteria import Misclassification
from foolbox.attacks import L2CarliniWagnerAttack

num_classes = 12

print("Step 1: Load model and weights")
baseModel = ResNet50(weights=None, include_top=False, input_tensor=Input(shape=(224, 224, 3)))
headModel = baseModel.output
headModel = Flatten(name="flatten")(headModel)
headModel = Dense(512, activation="relu")(headModel)
headModel = Dropout(0.5)(headModel)
headModel = Dense(num_classes, activation="softmax")(headModel)
model = Model(inputs=baseModel.input, outputs=headModel)

bounds = (0, 1)
fmodel = TensorFlowModel(model, bounds=bounds)
images, labels = tf.random.normal((64, 10, 224, 224, 3)), tf.random.uniform((64, 10,), maxval=13, dtype=tf.int32)

for i in range(0, images.shape[0]):

    print("document "+str(i))
    features_to_test=images[i,:]
    labels_to_test=labels[i,:]

    epsilons = np.linspace(0.01, 1, num=2)
    attack = L2CarliniWagnerAttack()
    adversarials = attack(fmodel, features_to_test, criterion=Misclassification(labels_to_test), epsilons=epsilons)

Step 1: Load model and weights
document 0
document 1
document 2
document 3
document 4
document 5
document 6
...

Dziękuję za odpowiedź, to działa! jedno pytanie: dlaczego do tej metody potrzebne są эпсилоны? wygląda na to, podejście w jego realizacjach nie robi tego domyślnie. Jeszcze raz dziękuję.
Tak, to jest dobre pytanie.. dokumenty wydają się dość skomplikowane.

Nie można uruchomić atak Карлини i Wagnera z pomocą foolbox w modelu тензорного przepływu

Pytanie

Najlepsza odpowiedź

W innych językach

Ta strona jest w innych językach

Popularne w tej kategorii

Najczęściej zadawane pytania w tej kategorii