ma_cisco_malware/main.py

import argparse

from keras.utils import np_utils

import dataset
import models

parser = argparse.ArgumentParser()

# parser.add_argument("--modes", action="store", dest="modes", nargs="+")

parser.add_argument("--train", action="store", dest="train_data",
                    default="data/full_dataset.csv.tar.bz2")

parser.add_argument("--test", action="store", dest="test_data",
                    default="data/full_future_dataset.csv.tar.bz2")

# parser.add_argument("--h5data", action="store", dest="h5data",
#                     default="")
#
parser.add_argument("--model", action="store", dest="model",
                    default="model_x")

# parser.add_argument("--pred", action="store", dest="pred",
#                     default="")
#
# parser.add_argument("--type", action="store", dest="model_type",
#                     default="simple_conv")
#
parser.add_argument("--batch", action="store", dest="batch_size",
                    default=64, type=int)

parser.add_argument("--epochs", action="store", dest="epochs",
                    default=10, type=int)

# parser.add_argument("--samples", action="store", dest="samples",
#                     default=100000, type=int)
#
# parser.add_argument("--samples_val", action="store", dest="samples_val",
#                     default=10000, type=int)
#
parser.add_argument("--embd", action="store", dest="embedding",
                    default=128, type=int)

parser.add_argument("--hidden_char_dims", action="store", dest="hidden_char_dims",
                    default=256, type=int)

parser.add_argument("--window", action="store", dest="window",
                    default=10, type=int)

parser.add_argument("--domain_length", action="store", dest="domain_length",
                    default=40, type=int)

parser.add_argument("--domain_embd", action="store", dest="domain_embedding",
                    default=512, type=int)

# parser.add_argument("--queue", action="store", dest="queue_size",
#                     default=50, type=int)
#
# parser.add_argument("--p", action="store", dest="p_train",
#                     default=0.5, type=float)
#
# parser.add_argument("--p_val", action="store", dest="p_val",
#                     default=0.01, type=float)
#
# parser.add_argument("--gpu", action="store", dest="gpu",
#                     default=0, type=int)
#
# parser.add_argument("--tmp", action="store_true", dest="tmp")
#
# parser.add_argument("--test", action="store_true", dest="test")

args = parser.parse_args()


# config = tf.ConfigProto(log_device_placement=True)
# config.gpu_options.per_process_gpu_memory_fraction = 0.5
# config.gpu_options.allow_growth = True
# session = tf.Session(config=config)


def main():
    # parameter
    cnnDropout = 0.5
    cnnHiddenDims = 1024
    numCiscoFeatures = 30
    kernel_size = 3
    drop_out = 0.5
    filters = 128
    network = models.pauls_networks

    char_dict = dataset.get_character_dict()
    user_flow_df = dataset.get_user_flow_data(args.train_data)

    print("create training dataset")
    domain_tr, flow_tr, client_tr, server_tr = dataset.create_dataset_from_flows(
        user_flow_df, char_dict,
        max_len=args.domain_length, window_size=args.window)

    shared_cnn = network.get_embedding(len(char_dict) + 1, args.embedding, args.domain_length,
                                       args.hidden_char_dims, kernel_size, args.domain_embedding, 0.5)
    shared_cnn.summary()

    model = network.get_model(cnnDropout, flow_tr.shape[-1], args.domain_embedding,
                              args.window, args.domain_length, filters, kernel_size,
                              cnnHiddenDims, shared_cnn)
    model.summary()

    model.compile(optimizer='adam',
                  loss='binary_crossentropy',
                  metrics=['accuracy'])

    client_tr = np_utils.to_categorical(client_tr, 2)
    server_tr = np_utils.to_categorical(server_tr, 2)
    model.fit([domain_tr, flow_tr],
              [client_tr, server_tr],
              batch_size=args.batch_size,
              epochs=args.epochs,
              shuffle=True,
              validation_split=0.2)


def main_train():
    pass


def main_test():
    char_dict = dataset.get_character_dict()
    user_flow_df = dataset.get_user_flow_data(args.test_data)
    domain_val, flow_val, client_val, server_val = dataset.create_dataset_from_flows(
        user_flow_df, char_dict,
        max_len=args.domain_length, window_size=args.window)
    # TODO: get model and exec model.evaluate(...)


if __name__ == "__main__":
    main()