from keras.models import *
from keras.optimizers import Adam
from malware_classification import common_process_data as read_data
from keras.layers import Input, LSTM, Bidirectional, Conv2D, Reshape
batch_size = 64
TIME_STEPS = 25
INPUT_DIM = 25
lstm_units = 128
num_classes = 15
epochs = 40
# data pre-processing
# (X_train, y_train), (X_test, y_test) = mnist.load_data('mnist.npz')
(X_train, y_train), (X_test, y_test) = read_data.load_npz_data(
"F:/数据集/Kim2016/malware_dataset/malware_dataset/attention_train_test_data.npz"
)
X_train = X_train.reshape(-1, 25, 25, 1) / 255.
X_test = X_test.reshape(-1, 25, 25, 1) / 255.
y_train = np_utils.to_categorical(y_train, num_classes=num_classes)
y_test = np_utils.to_categorical(y_test, num_classes=num_classes)
print('X_train shape:', X_train.shape)
print('X_test shape:', X_test.shape)
# build RNN model with attention
inputs = Input(shape=(25, 25, 1))
# build CNN model linked RNN outputs
x = Conv2D(filters=128,
kernel_size=(5, 5),
padding='same',
import time
from malware_classification.Self_Attention import Self_Attention_Layer
from malware_classification import common_process_data as read_data
from malware_classification import global_var as GLVAR
from keras.models import Model
from keras.layers import *
max_features = GLVAR.TOTAL_OPERATIONS_COUNT + 1 # 该数要比operation的个数大1
epochs = 25
batch_size = 32
print('Loading data...')
(x_train,
y_train), (x_test,
y_test) = read_data.load_npz_data(GLVAR.TRAIN_AND_TEST_DATA)
X_train = x_train.reshape(-1, GLVAR.pic_pow_size *
GLVAR.pic_pow_size) # why / 255?
X_test = x_test.reshape(-1, GLVAR.pic_pow_size * GLVAR.pic_pow_size)
# 标签转换为独热码
y_train = np_utils.to_categorical(y_train, num_classes=GLVAR.NUM_CLASSES)
y_test = np_utils.to_categorical(y_test, num_classes=GLVAR.NUM_CLASSES)
print(len(x_train), 'train sequences')
print(len(x_test), 'test sequences')
# %%数据归一化处理
maxlen = GLVAR.pic_pow_size * GLVAR.pic_pow_size
print('x_train shape:', x_train.shape)
print("cnn_x_test length is:", len(cnn_x_test.shape))
cnn_x_train = cnn_x_train.reshape(-1,64,32,1)
cnn_x_test = cnn_x_test.reshape(-1,64,32,1)
print(cnn_x_train.shape)
print(cnn_x_test.shape)
np.savez(GLVAR.MULTY_BINARY_CNN_TRAIN_TEST_DATA, x_train=cnn_x_train, x_test=cnn_x_test, y_train=y_train,y_test=y_test)
'''
max_features = 1000 # 该数要比operation的个数大1
maxlen = 2048
(x_train, y_train), (x_test, y_test) = read_data.load_npz_data(
GLVAR.MULTY_BINARY_CNN_TRAIN_TEST_DATA)
x_train = x_train.reshape(-1, 2048)
x_test = x_test.reshape(-1, 2048)
S_inputs = Input(shape=(maxlen, ), dtype='float32')
embeddings = Embedding(max_features, 256)(S_inputs)
O_seq = Self_Attention_Layer(256)(embeddings)
O_seq = GlobalAveragePooling1D()(O_seq)
# O_seq = Dropout(0.5)(O_seq)
outputs = Dense(GLVAR.NUM_CLASSES, activation='softmax')(O_seq)
def train_self_attention(lable_name, epochs, batch_size, score_filename):
print("================training ", lable_name, ".......================")
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
gpu_options = tf.GPUOptions(allow_growth=True)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
keras.backend.set_session(sess)
max_features = GLVAR.TOTAL_OPERATIONS_COUNT + 1 # 该数要比operation的个数大1
print('Loading data...')
current_lable_data = GLVAR.MULTY_BINARY_TRAIN_AND_TEST_DATA_DIR + lable_name + '.npz'
print("Current lable train and test data dir is : %s" %
(current_lable_data))
(x_train, y_train), (x_test,
y_test) = read_data.load_npz_data(current_lable_data)
x_train = x_train.reshape(-1, GLVAR.pic_pow_size *
GLVAR.pic_pow_size) # why / 255?
x_test = x_test.reshape(-1, GLVAR.pic_pow_size * GLVAR.pic_pow_size)
# 标签转换为独热码
y_train = np_utils.to_categorical(
y_train, num_classes=GLVAR.NUM_CLASSES_OF_MULTY_BINARY)
y_test = np_utils.to_categorical(
y_test, num_classes=GLVAR.NUM_CLASSES_OF_MULTY_BINARY)
print(len(x_train), 'train sequences')
print(len(x_test), 'test sequences')
# %%数据归一化处理
maxlen = GLVAR.pic_pow_size * GLVAR.pic_pow_size
print('x_train shape:', x_train.shape)
print('x_test shape:', x_test.shape)
S_inputs = Input(shape=(maxlen, ), dtype='int32')
embeddings = Embedding(maxlen, 256)(S_inputs)
O_seq = Self_Attention_Layer(256)(embeddings)
O_seq = GlobalAveragePooling1D()(O_seq)
O_seq = Dropout(0.5)(O_seq)
O_seq = Dense(16, activation='softmax')(O_seq)
outputs = Dense(GLVAR.NUM_CLASSES_OF_MULTY_BINARY,
activation='softmax')(O_seq)
model = Model(inputs=S_inputs, outputs=outputs)
print(model.summary())
# try using different optimizers and different optimizer configs
recall = keras_metrics.binary_recall(label=0)
# 使用适于二分类的loss函数 binary_crossentropy
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy', recall])
# %%
print('Training')
h = model.fit(x_train,
y_train,
batch_size=batch_size,
epochs=epochs,
validation_data=(x_test, y_test))
model_filename = GLVAR.MULTY_BINARY_SELF_ATTENTION_MODEL_DIR + lable_name + ".h5"
model.save(model_filename)
plt.plot(h.history["loss"], label="train_loss")
plt.plot(h.history["val_loss"], label="val_loss")
plt.plot(h.history["acc"], label="train_acc")
plt.plot(h.history["val_acc"], label="val_acc")
plt.legend()
plt.show()
print("-----------------------DY Add------------------------")
show_train_history(h, 'acc', 'val_acc', epochs)
show_train_history(h, 'loss', 'val_loss', epochs)
print('Testing--------------')
loss, accuracy, recall = model.evaluate(x_test,
y_test,
batch_size=batch_size)
print('test loss:', loss)
print('test accuracy:', accuracy)
print('test recall:', recall)
print("\t[Info] Accuracy of testing data = {:2.1f}%".format(accuracy *
100.0))
score = "----------" + lable_name + "----------\n" + "test loss:" + str(
format(loss, '.2f')) + "%\ntest accuracy:" + str(
format(accuracy, '.2f')) + "%\ntest recall:" + str(
format(recall, '.2f')) + "%\n"
with open(score_filename, "a") as f:
f.write(score)
from matplotlib import pyplot as plt
import time
from malware_classification.Self_Attention import Self_Attention_Layer
from malware_classification import common_process_data as read_data
from malware_classification import global_var as GLVAR
from keras.models import Model
from keras.layers import *
max_features = GLVAR.TOTAL_OPERATIONS_COUNT + 1 # 该数要比operation的个数大1
epochs=30
batch_size = 32
print('Loading data...')
(x_train, y_train), (x_test, y_test) = read_data.load_npz_data(GLVAR.TRAIN_AND_TEST_DATA)
X_train = x_train.reshape(-1,GLVAR.pic_pow_size * GLVAR.pic_pow_size) # why / 255?
X_test = x_test.reshape(-1,GLVAR.pic_pow_size * GLVAR.pic_pow_size)
# 标签转换为独热码
y_train = np_utils.to_categorical(y_train, num_classes=GLVAR.NUM_CLASSES)
y_test = np_utils.to_categorical(y_test, num_classes=GLVAR.NUM_CLASSES)
print(len(x_train), 'train sequences')
print(len(x_test), 'test sequences')
# %%数据归一化处理
maxlen = GLVAR.pic_pow_size * GLVAR.pic_pow_size
print('x_train shape:', x_train.shape)
print('x_test shape:', x_test.shape)
