실행할 수 없습니다 Carlini 및 Wagner 공격을 사용하여 foolbox 에 tensorflow 모델

0

질문

나의 최신 버전을 사용하여 foolbox(3.3.1),나의 코드 간단히드 RESNET-50 현지 추가,몇 가지 레이어에 대 한 전송 학습 프로그램,로드 중량으로 다음과 같습니다.

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")

지금 나는 그것을 공격을 사용하여 foolbox3.3.1Carlini 및 Wagner 공격에,여기에는 방법이 나는 부하에 대한 모델 foolbox

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

나의 데이터 집합으로 분의 10 이미지당 문서,나는 공격한 이러한 10 개의 이미지를 사용하여 배치의 크기를 10foolbox 를 사용하여 Carlini 및 Wagner 공격

#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)

그러나 때마다 실행 코드,여기에 오류는 반환하는 날

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'

무엇을 해야하는 오류? 나는 선적 모델이 잘못? 에 추가해야 하는 새로운 매개 변수에 대한 공격이라는? 앞에서 설명한 것처럼,나는 foolbox3.3.1.

1

최고의 응답

1

나는 생각이 있을 수 있습 혼합의 매개변수 L2CarliniWagnerAttack. 여기에 간단한 예로미터:

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
...
2021-11-23 12:13:46

답변 주셔서 감사합니다,그것은 작품! 질문 하나,왜 이 방법이 필요 epsilons? 그것은 보인 접근 구현하지 않는 기본적으로 합니다. 다시 한번 감사드립니다.
mad

네 좋은 질문입니다..docs 것 같다 꽤 복잡하다.
AloneTogether

다른 언어로

이 페이지는 다른 언어로되어 있습니다

Русский
..................................................................................................................
Italiano
..................................................................................................................
Polski
..................................................................................................................
Română
..................................................................................................................
हिन्दी
..................................................................................................................
Français
..................................................................................................................
Türk
..................................................................................................................
Česk
..................................................................................................................
Português
..................................................................................................................
ไทย
..................................................................................................................
中文
..................................................................................................................
Español
..................................................................................................................
Slovenský
..................................................................................................................