def test_untargeted_Xception(image, label=None):
import keras
from perceptron.models.classification.keras import KerasModel
mean = np.array([0.485, 0.456, 0.406]).reshape((1, 1, 3))
std = np.array([0.229, 0.224, 0.225]).reshape((1, 1, 3))
model_keras = keras.applications.xception.Xception(weights='imagenet')
model = KerasModel(model_keras, bounds=(0, 1), preprocessing=(mean, std))
print(np.argmax(model.predictions(image)))
attack = Attack(model, criterion=Misclassification())
adversarial_obj = attack(image, label, unpack=False, epsilons=10000)
distance = adversarial_obj.distance
adversarial = adversarial_obj.image
return distance, adversarial
import keras.applications as models
from perceptron.models.classification.keras import KerasModel
from perceptron.utils.image import imagenet_example
from perceptron.benchmarks.additive_noise import AdditiveGaussianNoiseMetric
from perceptron.utils.criteria.classification import TopKMisclassification
from perceptron.utils.tools import plot_image
from perceptron.utils.tools import bcolors
# instantiate the model from keras applications
xception = models.Xception(weights='imagenet')
# initialize the KerasModel
# keras xception has input bound (0, 1)
mean = np.array([0.485, 0.456, 0.406]).reshape((1, 1, 3))
std = np.array([0.229, 0.224, 0.225]).reshape((1, 1, 3))
kmodel = KerasModel(xception, bounds=(0, 1), preprocessing=(mean, std))
# get source image and label
# the model Xception expects values in [0, 1] with shape (299, 299), and channles_last
image, _ = imagenet_example(shape=(299, 299), data_format='channels_last')
image /= 255.0
label = np.argmax(kmodel.predictions(image))
metric = AdditiveGaussianNoiseMetric(kmodel,
criterion=TopKMisclassification(10))
print(bcolors.BOLD + 'Process start' + bcolors.ENDC)
adversary = metric(
image, label, unpack=False,
epsilons=1000) # choose 1000 different epsilon values in [0, 1]
print(bcolors.BOLD + 'Process finished' + bcolors.ENDC)
import keras.applications as models
from perceptron.models.classification.keras import KerasModel
from perceptron.utils.image import imagenet_example
from perceptron.benchmarks.blended_noise import BlendedUniformNoiseMetric
from perceptron.utils.criteria.classification import TopKMisclassification
from perceptron.utils.tools import plot_image
from perceptron.utils.tools import bcolors
# instantiate the model from keras applications
vgg16 = models.VGG16(weights='imagenet')
# initialize the KerasModel
# keras vgg16 has input bound (0, 255)
preprocessing = (np.array([104, 116,
123]), 1) # the mean and stv of the whole dataset
kmodel = KerasModel(vgg16, bounds=(0, 255), preprocessing=preprocessing)
# get source image and label
# the model expects values in [0, 255], and channles_last
image, _ = imagenet_example(data_format='channels_last')
label = np.argmax(kmodel.predictions(image))
metric = BlendedUniformNoiseMetric(kmodel, criterion=TopKMisclassification(10))
print(bcolors.BOLD + 'Process start' + bcolors.ENDC)
adversary = metric(
image, label, unpack=False,
epsilons=100) # choose 100 different epsilon values in [0, 1]
print(bcolors.BOLD + 'Process finished' + bcolors.ENDC)
if adversary.image is None: