def gen_data(model_name, use_adv=True, deepxplore=False):
model_path = model_conf.get_model_path(model_conf.svhn, model_name) #
(X_train, Y_train), (X_test, Y_test) = SVNH_DatasetUtil.load_data()
Y_test = np.argmax(Y_test, axis=1)
# model_path = './model/model_svhn.hdf5'
if use_adv:
attack_lst = ['cw', 'fgsm', 'jsma', 'bim']
adv_image_all = []
adv_label_all = []
for attack in attack_lst:
im, lab = model_conf.get_adv_path(attack, model_conf.svhn, model_name)
adv_image_all.append(np.load(im))
adv_label_all.append(np.load(lab))
adv_image_all = np.concatenate(adv_image_all, axis=0)
adv_label_all = np.concatenate(adv_label_all, axis=0)
print("adv: ", len(adv_image_all))
test = np.concatenate([X_test, adv_image_all], axis=0)
true_test = np.concatenate([Y_test, adv_label_all], axis=0)
else:
test = X_test
true_test = Y_test
train = X_train
model = load_model(model_path)
model.summary()
pred_test_prob = model.predict(test)
pred_test = np.argmax(pred_test_prob, axis=1)
input = model.layers[0].output
# print(dir(model.layers[0]))
# print(input)
if not deepxplore:
if model_name == model_conf.LeNet5:
layers = [model.layers[2].output, model.layers[3].output, model.layers[5].output, model.layers[6].output,
model.layers[8].output, model.layers[9].output, model.layers[10].output]
layers = list(zip(4 * ['conv'] + 3 * ['dense'], layers))
else: # Vgg16
layers = []
for i in range(1, 19):
layers.append(model.layers[i].output)
for i in range(20, 23):
layers.append(model.layers[i].output)
layers = list(zip(18 * ['conv'] + 3 * ['dense'], layers))
else:
if model_name == model_conf.LeNet5:
layers = [model.layers[1].output, model.layers[3].output, model.layers[4].output, model.layers[8].output,
model.layers[8].output, model.layers[9].output, model.layers[10].output]
layers = list(zip(4 * ['conv'] + 3 * ['dense'], layers))
else:
layers = []
for i in range(1, 19):
layers.append(model.layers[i].output)
for i in range(20, 23):
layers.append(model.layers[i].output)
layers = list(zip(18 * ['conv'] + 3 * ['dense'], layers))
# print(len(layers), layers)
return input, layers, test, train, pred_test, true_test, pred_test_prob
def gen_data(name, model_name, nb_classes=10):
X_train, X_val, X_test, Y_train, Y_val, Y_test = None, None, None, None, None, None
if name.startswith("mnist"):
X_train, X_test, Y_train, Y_test, = gen_data_mnist() # 获得原始数据集
elif name.startswith("fashion"):
X_train, X_test, Y_train, Y_test, = gen_data_fashion() # 获得原始数据集
elif name.startswith("svhn"):
X_train, X_test, Y_train, Y_test, = gen_data_svhn() # 获得原始数据集
elif name.startswith("cifar"):
X_train, X_test, Y_train, Y_test, = gen_data_cifar() # 获得原始数据集
attack_lst = ['cw', 'fgsm', 'jsma', 'bim']
adv_image_test_arr = []
adv_label_test_arr = []
for attack in attack_lst:
im, lab = model_conf.get_adv_path(attack, name, model_name)
attack_test = np.load(im)
attack_lable = np.load(lab)
adv_image_test_arr.append(attack_test)
adv_label_test_arr.append(attack_lable)
adv_X_test = np.concatenate(adv_image_test_arr, axis=0)
adv_Y_test = np.concatenate(adv_label_test_arr, axis=0)
adv_Y_test = np_utils.to_categorical(adv_Y_test, nb_classes)
X_test = adv_X_test
Y_test = adv_Y_test
# 1w条数据
# adv_X_test, _, adv_Y_test, _ = train_test_split(adv_X_test, adv_Y_test, train_size=5000, random_state=42)
# X_test, _, Y_test, _ = train_test_split(X_test, Y_test, train_size=5000, random_state=42)
# X_test = np.r_[X_test, adv_X_test] # 共1w条
# Y_test = np.r_[Y_test, adv_Y_test]
# adv_X_test, _, adv_Y_test, _ = train_test_split(adv_X_test, adv_Y_test, train_size=5000)
# X_test, _, Y_test, _ = train_test_split(X_test, Y_test, train_size=5000)
# adv_Y_test = np_utils.to_categorical(adv_Y_test, nb_classes)
# X_test = np.concatenate([X_test, adv_X_test], axis=0) # 共1w条 2000:8000
# Y_test = np.concatenate([Y_test, adv_Y_test], axis=0)
return X_train, X_test, Y_train, Y_test
def gen_data(model_name, use_adv=True, deepxplore=False):
# path = './fashion-mnist/data/fashion'
# X_train, Y_train = mnist_reader.load_mnist(path, kind='train')
# X_test, Y_test = mnist_reader.load_mnist(path, kind='t10k')
# X_train = X_train.astype('float32').reshape(-1, 28, 28, 1)
# X_test = X_test.astype('float32').reshape(-1, 28, 28, 1)
# X_train /= 255
# X_test /= 255
### modify
(X_train, y_train), (X_test,
Y_test) = fashion_mnist.load_data() ### modify
X_train = X_train.astype('float32').reshape(-1, 28, 28, 1)
X_test = X_test.astype('float32').reshape(-1, 28, 28, 1)
X_train /= 255
X_test /= 255
model_path = model_conf.get_model_path(model_conf.fashion, model_name)
if use_adv:
attack_lst = ['fgsm', 'jsma', 'bim', 'cw']
adv_image_all = []
adv_label_all = []
for attack in attack_lst:
im, lab = model_conf.get_adv_path(attack, model_conf.fashion,
model_name)
adv_image_all.append(np.load(im))
adv_label_all.append(np.load(lab))
adv_image_all = np.concatenate(adv_image_all, axis=0)
adv_label_all = np.concatenate(adv_label_all, axis=0)
print("adv: ", len(adv_image_all))
test = np.concatenate([X_test, adv_image_all], axis=0)
true_test = np.concatenate([Y_test, adv_label_all], axis=0)
else:
test = X_test
true_test = Y_test
train = X_train
model = load_model(model_path)
pred_test_prob = model.predict(test)
pred_test = np.argmax(pred_test_prob, axis=1)
input = model.layers[0].output
lst = []
for index, layer in enumerate(model.layers):
if 'activation' in layer.name:
lst.append(index)
lst.append(len(model.layers) - 1)
# 是否deepxplore
if not deepxplore:
if model_name == model_conf.LeNet5: # 选择模型
layers = [
model.layers[2].output, model.layers[3].output,
model.layers[5].output, model.layers[6].output,
model.layers[8].output, model.layers[9].output,
model.layers[10].output
]
layers = list(zip(4 * ['conv'] + 3 * ['dense'], layers))
elif model_name == model_conf.LeNet1: # LeNet1
layers = [
model.layers[2].output,
model.layers[3].output,
model.layers[5].output,
model.layers[6].output,
model.layers[8].output,
]
# print(model.layers[1], model.layers[3], model.layers[6])
layers = list(zip(4 * ['conv'] + 1 * ['dense'], layers)) #
else: # ResNet20
layers = []
for index in lst:
layers.append(model.layers[index].output)
layers = list(zip(19 * ['conv'] + 1 * ['dense'], layers))
else:
if model_name == model_conf.LeNet5:
layers = [
model.layers[1].output, model.layers[3].output,
model.layers[4].output, model.layers[8].output,
model.layers[8].output, model.layers[9].output,
model.layers[10].output
]
layers = list(zip(4 * ['conv'] + 3 * ['dense'], layers))
elif model_name == model_conf.LeNet1: # LeNet1
layers = [
model.layers[1].output,
model.layers[3].output,
model.layers[4].output,
model.layers[6].output,
model.layers[8].output,
]
layers = list(zip(4 * ['conv'] + 1 * ['dense'], layers))
else:
layers = []
for index in lst:
if index != len(model.layers) - 1:
layers.append(model.layers[index - 1].output)
else:
layers.append(model.layers[index].output)
layers = list(zip(19 * ['conv'] + 1 * ['dense'], layers))
return input, layers, test, train, pred_test, true_test, pred_test_prob
# print("update csv")
# df = pd.read_csv(path, index_col=0)
# for k, v in dic.items():
# df[k] = v
# df.to_csv(path)
if __name__ == '__main__':
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
x = "./all_output/output_fashion/resNet20/"
if not os.path.exists(x):
os.makedirs(x)
x = "./all_output/output_fashion/LeNet1/"
if not os.path.exists(x):
os.makedirs(x)
model_name = model_conf.LeNet1
exec(model_name)
print("dataset", "model_name")
print(model_conf.fashion, model_name)
print("adv path")
print(model_conf.get_adv_path("cw", model_conf.fashion,
model_name)) # 39992
print("================================================================")
model_name = model_conf.resNet20
exec(model_name)
print("dataset", "model_name")
print(model_conf.fashion, model_name)
print("adv path")
print(model_conf.get_adv_path("cw", model_conf.fashion, model_name))
def gen_data_cifar(model_name, use_adv=True, deepxplore=False):
model_path = model_conf.get_model_path(model_conf.cifar10, model_name)
(X_train, Y_train), (X_test, Y_test) = cifar10.load_data() # 32*32
X_train = X_train.astype('float32').reshape(-1, 32, 32, 3)
X_test = X_test.astype('float32').reshape(-1, 32, 32, 3)
X_train /= 255
X_test /= 255
Y_train = Y_train.reshape(-1)
Y_test = Y_test.reshape(-1)
# model_path = './model/model_cifar10.h5'
if use_adv:
attack_lst = ['cw', 'fgsm', 'jsma', 'bim']
adv_image_all = []
adv_label_all = []
for attack in attack_lst:
im, lab = model_conf.get_adv_path(attack, model_conf.cifar10,
model_name)
adv_image_all.append(np.load(im))
adv_label_all.append(np.load(lab))
adv_image_all = np.concatenate(adv_image_all, axis=0)
adv_label_all = np.concatenate(adv_label_all, axis=0)
test = np.concatenate([X_test, adv_image_all], axis=0)
true_test = np.concatenate([Y_test, adv_label_all], axis=0)
else:
test = X_test
true_test = Y_test
train = X_train
model = load_model(model_path)
pred_test_prob = model.predict(test)
pred_test = np.argmax(pred_test_prob, axis=1)
input = model.layers[0].output
lst = []
for index, layer in enumerate(model.layers):
if 'activation' in layer.name:
lst.append(index)
lst.append(len(model.layers) - 1)
if not deepxplore:
if model_name == model_conf.resNet20:
layers = []
for index in lst:
layers.append(model.layers[index].output)
layers = list(zip(19 * ['conv'] + 1 * ['dense'], layers))
else: # Vgg16
layers = []
for i in range(1, 19):
layers.append(model.layers[i].output)
for i in range(20, 23):
layers.append(model.layers[i].output)
layers = list(zip(18 * ['conv'] + 3 * ['dense'], layers))
else:
if model_name == model_conf.resNet20:
layers = []
for index in lst:
if index != len(model.layers) - 1:
layers.append(model.layers[index - 1].output)
else:
layers.append(model.layers[index].output)
layers = list(zip(19 * ['conv'] + 1 * ['dense'], layers))
else:
layers = []
for i in range(1, 19):
layers.append(model.layers[i].output)
for i in range(20, 23):
layers.append(model.layers[i].output)
layers = list(zip(18 * ['conv'] + 3 * ['dense'], layers))
return input, layers, test, train, pred_test, true_test, pred_test_prob, Y_train
def gen_data_svhn(model_name, use_adv=True, deepxplore=False):
model_path = model_conf.get_model_path(model_conf.svhn, model_name) #
(X_train, Y_train), (X_test, Y_test) = SVNH_DatasetUtil.load_data()
Y_train = np.argmax(Y_train, axis=1) # modify 原本是一堆矩阵,[0,0,0,1,0]代表第四类
Y_test = np.argmax(Y_test, axis=1)
if use_adv:
attack_lst = ['cw', 'fgsm', 'jsma', 'bim']
adv_image_all = []
adv_label_all = []
for attack in attack_lst:
im, lab = model_conf.get_adv_path(attack, model_conf.svhn,
model_name)
adv_image_all.append(np.load(im))
adv_label_all.append(np.load(lab))
adv_image_all = np.concatenate(adv_image_all, axis=0)
adv_label_all = np.concatenate(adv_label_all, axis=0)
test = np.concatenate([X_test, adv_image_all], axis=0)
true_test = np.concatenate([Y_test, adv_label_all], axis=0)
else:
test = X_test
true_test = Y_test
train = X_train
model = load_model(model_path)
pred_test_prob = model.predict(test)
pred_test = np.argmax(pred_test_prob, axis=1)
input = model.layers[0].output
lst = []
for index, layer in enumerate(model.layers):
if 'activation' in layer.name:
lst.append(index)
lst.append(len(model.layers) - 1)
if not deepxplore:
if model_name == model_conf.LeNet5:
layers = [
model.layers[2].output, model.layers[3].output,
model.layers[5].output, model.layers[6].output,
model.layers[8].output, model.layers[9].output,
model.layers[10].output
]
layers = list(zip(4 * ['conv'] + 3 * ['dense'], layers))
else: # Vgg16
layers = []
for i in range(1, 19):
layers.append(model.layers[i].output)
for i in range(20, 23):
layers.append(model.layers[i].output)
layers = list(zip(18 * ['conv'] + 3 * ['dense'], layers))
else:
if model_name == model_conf.LeNet5:
layers = [
model.layers[1].output, model.layers[3].output,
model.layers[4].output, model.layers[8].output,
model.layers[8].output, model.layers[9].output,
model.layers[10].output
]
layers = list(zip(4 * ['conv'] + 3 * ['dense'], layers))
else:
layers = []
for i in range(1, 19):
layers.append(model.layers[i].output)
for i in range(20, 23):
layers.append(model.layers[i].output)
layers = list(zip(18 * ['conv'] + 3 * ['dense'], layers))
return input, layers, test, train, pred_test, true_test, pred_test_prob, Y_train
def gen_data_mnist(
model_name,
use_adv=False,
deepxplore=False,
):
model_path = model_conf.get_model_path(model_conf.mnist, model_name) #
(X_train, Y_train), (X_test, Y_test) = mnist.load_data() # 28*28
X_train = X_train.astype('float32').reshape(-1, 28, 28, 1)
X_test = X_test.astype('float32').reshape(-1, 28, 28, 1)
X_train /= 255
X_test /= 255
# model_path = './model/model_mnist.hdf5'
if use_adv:
attack_lst = ['fgsm', 'jsma', 'bim', 'cw']
adv_image_all = []
adv_label_all = []
for attack in attack_lst:
im, lab = model_conf.get_adv_path(attack, model_conf.mnist,
model_name)
adv_image_all.append(np.load(im))
adv_label_all.append(np.load(lab))
adv_image_all = np.concatenate(adv_image_all, axis=0)
adv_label_all = np.concatenate(adv_label_all, axis=0)
test = np.concatenate([X_test, adv_image_all], axis=0)
true_test = np.concatenate([Y_test, adv_label_all], axis=0)
else:
test = X_test
true_test = Y_test
train = X_train
model = load_model(model_path)
pred_test_prob = model.predict(test)
pred_test = np.argmax(pred_test_prob, axis=1)
input = model.layers[0].output
if not deepxplore: #
if model_name == model_conf.LeNet5:
layers = [
model.layers[2].output, model.layers[3].output,
model.layers[5].output, model.layers[6].output,
model.layers[8].output, model.layers[9].output,
model.layers[10].output
]
layers = list(zip(4 * ['conv'] + 3 * ['dense'],
layers)) # 激活,池化,全连接
else:
layers = [
model.layers[2].output,
model.layers[3].output,
model.layers[5].output,
model.layers[6].output,
model.layers[8].output,
]
# print(model.layers[1], model.layers[3], model.layers[6])
layers = list(zip(4 * ['conv'] + 1 * ['dense'], layers)) #
else:
if model_name == model_conf.LeNet5:
layers = [
model.layers[1].output, model.layers[3].output,
model.layers[4].output, model.layers[8].output,
model.layers[8].output, model.layers[9].output,
model.layers[10].output
]
layers = list(zip(4 * ['conv'] + 3 * ['dense'],
layers)) # 卷积,池化,全连接
else:
layers = [
model.layers[1].output,
model.layers[3].output,
model.layers[4].output,
model.layers[6].output,
model.layers[8].output,
]
layers = list(zip(4 * ['conv'] + 1 * ['dense'], layers))
return input, layers, test, train, pred_test, true_test, pred_test_prob, Y_train
dic['mnist_adv_snac_std_1'] = (start - end)
start = time.time()
exp(model_name, coverage='snac', use_adv=True, std=0)
end = time.time()
dic['mnist_adv_snac_std_0'] = (start - end)
if __name__ == '__main__':
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
x = "./all_output/output_svhn/vgg16/"
if not os.path.exists(x):
os.makedirs(x)
model_name = model_conf.vgg16
exec(model_name)
print("dataset", "model_name")
print(model_conf.svhn, model_name)
print("adv path")
print(model_conf.get_adv_path("cw", model_conf.svhn, model_name))
print("================================================================")
x = "./all_output/output_svhn/LeNet5/"
if not os.path.exists(x):
os.makedirs(x)
model_name = model_conf.LeNet5
exec(model_name)
print("dataset", "model_name")
print(model_conf.svhn, model_name)
print("adv path")
print(model_conf.get_adv_path("cw", model_conf.svhn, model_name))
# else:
# print("update csv")
# df = pd.read_csv(path, index_col=0)
# for k, v in dic.items():
# df[k] = v
# df.to_csv(path)
if __name__ == '__main__':
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
x = "./all_output/output_cifar/vgg16/"
if not os.path.exists(x):
os.makedirs(x)
model_name = model_conf.vgg16
exec(model_name)
print("dataset", "model_name")
print(model_conf.cifar10, model_name)
print("adv path")
print(model_conf.get_adv_path("cw", model_conf.cifar10, model_name))
print("================================================================")
x = "./all_output/output_cifar/resNet20/"
if not os.path.exists(x):
os.makedirs(x)
model_name = model_conf.resNet20
exec(model_name)
print("dataset", "model_name")
print(model_conf.cifar10, model_name)
print("adv path")
print(model_conf.get_adv_path("cw", model_conf.cifar10, model_name))
start = time.time()
exp(model_name, coverage='snac', use_adv=True, std=0)
end = time.time()
dic['mnist_adv_snac_std_0'] = (start - end)
if __name__ == '__main__':
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
x = "./all_output/output_mnist/LeNet1/"
if not os.path.exists(x):
os.makedirs(x)
x = "./all_output/output_mnist/LeNet5/"
if not os.path.exists(x):
os.makedirs(x)
model_name = model_conf.LeNet1 # 39854
exec(model_name)
print("dataset", "model_name")
print(model_conf.mnist, model_name)
print("adv path")
print(model_conf.get_adv_path("cw", model_conf.mnist, model_name))
print("================================================================")
model_name = model_conf.LeNet5 # 39705
exec(model_name)
print("dataset", "model_name")
print(model_conf.mnist, model_name)
print("adv path")
print(model_conf.get_adv_path("cw", model_conf.mnist, model_name))
