ma_cisco_malware/main.py

import json
import logging
import os

import numpy as np
import pandas as pd
import tensorflow as tf
from keras.callbacks import ModelCheckpoint, CSVLogger, EarlyStopping
from keras.models import load_model
from keras.utils import np_utils
from sklearn.utils import class_weight

import arguments
import dataset
import hyperband
import models
# create logger
import visualize
from dataset import load_or_generate_h5data
from utils import exists_or_make_path

logger = logging.getLogger('logger')
logger.setLevel(logging.DEBUG)

# create console handler and set level to debug
ch = logging.StreamHandler()
ch.setLevel(logging.DEBUG)

# create formatter
formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')

# add formatter to ch
ch.setFormatter(formatter)

# add ch to logger
logger.addHandler(ch)

ch = logging.FileHandler("info.log")
ch.setLevel(logging.DEBUG)

# create formatter
formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')

# add formatter to ch
ch.setFormatter(formatter)

# add ch to logger
logger.addHandler(ch)

args = arguments.parse()

if args.gpu:
    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_paul_best():
    char_dict = dataset.get_character_dict()
    pauls_best_params = models.pauls_networks.best_config
    pauls_best_params["vocab_size"] = len(char_dict) + 1
    main_train(pauls_best_params)


def main_hyperband():
    char_dict = dataset.get_character_dict()

    params = {
        # static params
        "type": ["paul"],
        "batch_size": [args.batch_size],
        "vocab_size": [len(char_dict) + 1],
        "window_size": [10],
        "domain_length": [40],
        "flow_features": [3],
        "input_length": [40],
        # model params
        "embedding_size": [8, 16, 32, 64, 128, 256],
        "filter_embedding": [8, 16, 32, 64, 128, 256],
        "kernel_embedding": [1, 3, 5, 7, 9],
        "hidden_embedding": [8, 16, 32, 64, 128, 256],
        "dropout": [0.5],
        "domain_features": [8, 16, 32, 64, 128, 256],
        "filter_main": [8, 16, 32, 64, 128, 256],
        "kernels_main": [1, 3, 5, 7, 9],
        "dense_main": [8, 16, 32, 64, 128, 256],
    }

    logger.info("create training dataset")
    domain_tr, flow_tr, client_tr, server_tr = load_or_generate_h5data(args.train_h5data, args.train_data,
                                                                       args.domain_length, args.window)
    hp = hyperband.Hyperband(params,
                             [domain_tr, flow_tr],
                             [client_tr, server_tr])
    results = hp.run()
    json.dump(results, open("hyperband.json"))


def get_custom_class_weights(client_tr, server_tr):
    client = client_tr.value.argmax(1) if type(client_tr) != np.ndarray else client_tr.argmax(1)
    server = server_tr.value.argmax(1) if type(server_tr) != np.ndarray else server_tr.argmax(1)
    client_class_weight = class_weight.compute_class_weight('balanced', np.unique(client), client)
    server_class_weight = class_weight.compute_class_weight('balanced', np.unique(server), server)
    return {
        "client": client_class_weight,
        "server": server_class_weight
    }


def main_train(param=None):
    exists_or_make_path(args.model_path)

    char_dict = dataset.get_character_dict()
    domain_tr, flow_tr, client_tr, server_windows_tr = load_or_generate_h5data(args.train_h5data, args.train_data,
                                                                               args.domain_length, args.window)

    # parameter
    p = {
        "type": args.model_type,
        "batch_size": 64,
        "window_size": args.window,
        "domain_length": args.domain_length,
        "flow_features": 3,
        "vocab_size": len(char_dict) + 1,
        #
        'dropout': 0.5,
        'domain_features': args.domain_embedding,
        'embedding_size': args.embedding,
        'filter_main': 64,
        'flow_features': 3,
        # 'dense_main': 512,
        'dense_main': 64,
        'filter_embedding': args.hidden_char_dims,
        'hidden_embedding': args.domain_embedding,
        'kernel_embedding': 3,
        'kernels_main': 3,
        'input_length': 40
    }
    if not param:
        param = p

    embedding, model, _ = models.get_models_by_params(param)
    embedding.summary()
    model.summary()
    logger.info("define callbacks")
    callbacks = []
    callbacks.append(ModelCheckpoint(filepath=args.clf_model,
                                     monitor='val_loss',
                                     verbose=False,
                                     save_best_only=True))
    callbacks.append(CSVLogger(args.train_log))
    if args.stop_early:
        callbacks.append(EarlyStopping(monitor='val_loss',
                                       patience=5,
                                       verbose=False))
    logger.info("compile model")
    custom_metrics = models.get_metric_functions()
    model.compile(optimizer='adam',
                  loss='categorical_crossentropy',
                  metrics=['accuracy'] + custom_metrics)

    server_tr = np_utils.to_categorical(np.max(server_windows_tr, axis=1), 2)

    if args.class_weights:
        logger.info("class weights: compute custom weights")
        custom_class_weights = get_custom_class_weights(client_tr, server_tr)
        logger.info(custom_class_weights)
    else:
        logger.info("class weights: set default")
        custom_class_weights = None
    logger.info("start training")
    model.fit([domain_tr, flow_tr],
              [client_tr, server_tr],
              batch_size=args.batch_size,
              epochs=args.epochs,
              callbacks=callbacks,
              shuffle=True,
              validation_split=0.2,
              class_weight=custom_class_weights)
    logger.info("save embedding")
    embedding.save(args.embedding_model)


def main_test():
    domain_val, flow_val, client_val, server_val = load_or_generate_h5data(args.test_h5data, args.test_data,
                                                                           args.domain_length, args.window)
    clf = load_model(args.clf_model, custom_objects=models.get_metrics())
    # stats = clf.evaluate([domain_val, flow_val],
    #                      [client_val, server_val],
    #                      batch_size=args.batch_size)
    y_pred = clf.predict([domain_val, flow_val],
                         batch_size=args.batch_size,
                         verbose=1)
    np.save(args.future_prediction, y_pred)

    char_dict = dataset.get_character_dict()
    user_flow_df = dataset.get_user_flow_data(args.test_data)
    domains = user_flow_df.domain.unique()[:-1]

    def get_domain_features_reduced(d):
        return dataset.get_domain_features(d[0], char_dict, args.domain_length)

    domain_features = []
    for ds in domains:
        domain_features.append(np.apply_along_axis(get_domain_features_reduced, 2, np.atleast_3d(ds)))

    model = load_model(args.embedding_model)
    domain_features = np.stack(domain_features).reshape((-1, 40))
    pred = model.predict(domain_features, batch_size=args.batch_size, verbose=1)

    np.save("/tmp/rk/domains.npy", domains)
    np.save("/tmp/rk/domain_features.npy", domain_features)
    np.save("/tmp/rk/domain_embd.npy", pred)


def main_new_model():
    exists_or_make_path(args.model_path)

    char_dict = dataset.get_character_dict()
    domain_tr, flow_tr, client_tr, server_windows_tr = load_or_generate_h5data(args.train_h5data, args.train_data,
                                                                               args.domain_length, args.window)

    # parameter
    p = {
        "type": args.model_type,
        "batch_size": 64,
        "window_size": args.window,
        "domain_length": args.domain_length,
        "flow_features": 3,
        "vocab_size": len(char_dict) + 1,
        #
        'dropout': 0.5,
        'domain_features': args.domain_embedding,
        'embedding_size': args.embedding,
        'filter_main': 64,
        'flow_features': 3,
        # 'dense_main': 512,
        'dense_main': 64,
        'filter_embedding': args.hidden_char_dims,
        'hidden_embedding': args.domain_embedding,
        'kernel_embedding': 3,
        'kernels_main': 3,
        'input_length': 40
    }

    embedding, _, model = models.get_models_by_params(p)
    embedding.summary()
    model.summary()
    logger.info("define callbacks")
    callbacks = []
    callbacks.append(ModelCheckpoint(filepath=args.clf_model,
                                     monitor='val_loss',
                                     verbose=False,
                                     save_best_only=True))
    callbacks.append(CSVLogger(args.train_log))
    if args.stop_early:
        callbacks.append(EarlyStopping(monitor='val_loss',
                                       patience=5,
                                       verbose=False))
    logger.info("compile model")
    custom_metrics = models.get_metric_functions()
    model.compile(optimizer='adam',
                  loss='categorical_crossentropy',
                  metrics=['accuracy'] + custom_metrics)

    server_tr = np_utils.to_categorical(np.max(server_windows_tr, axis=1), 2)

    if args.class_weights:
        logger.info("class weights: compute custom weights")
        custom_class_weights = get_custom_class_weights(client_tr, server_tr)
        logger.info(custom_class_weights)
    else:
        logger.info("class weights: set default")
        custom_class_weights = None
    logger.info("start training")
    server_tr = np.stack(np_utils.to_categorical(s, 2) for s in server_windows_tr)
    model.fit([domain_tr, flow_tr],
              [client_tr, server_tr],
              batch_size=args.batch_size,
              epochs=args.epochs,
              callbacks=callbacks,
              shuffle=True,
              validation_split=0.2,
              class_weight=custom_class_weights)
    logger.info("save embedding")
    embedding.save(args.embedding_model)


def main_embedding():
    model = load_model(args.embedding_model)
    domain_encs, labels = dataset.load_or_generate_domains(args.train_data, args.domain_length)
    domain_embedding = model.predict(domain_encs, batch_size=args.batch_size, verbose=1)
    visualize.plot_embedding(domain_embedding, labels, path="results/pp3/embd.png")


def main_visualization():
    domain_val, flow_val, client_val, server_val = load_or_generate_h5data(args.test_h5data, args.test_data,
                                                                           args.domain_length, args.window)
    logger.info("plot model")
    model = load_model(args.clf_model, custom_objects=models.get_metrics())
    visualize.plot_model(model, os.path.join(args.model_path, "model.png"))
    try:
        logger.info("plot training curve")
        logs = pd.read_csv(args.train_log)
        visualize.plot_training_curve(logs, "client", "{}/client_train.png".format(args.model_path))
        visualize.plot_training_curve(logs, "server", "{}/server_train.png".format(args.model_path))
    except Exception as e:
        logger.warning(f"could not generate training curves: {e}")

    client_pred, server_pred = np.load(args.future_prediction)
    logger.info("plot pr curve")
    visualize.plot_precision_recall(client_val.value, client_pred, "{}/client_prc.png".format(args.model_path))
    visualize.plot_precision_recall(server_val.value, server_pred, "{}/server_prc.png".format(args.model_path))
    visualize.plot_precision_recall_curves(client_val.value, client_pred, "{}/client_prc2.png".format(args.model_path))
    visualize.plot_precision_recall_curves(server_val.value, server_pred, "{}/server_prc2.png".format(args.model_path))
    logger.info("plot roc curve")
    visualize.plot_roc_curve(client_val.value, client_pred, "{}/client_roc.png".format(args.model_path))
    visualize.plot_roc_curve(server_val.value, server_pred, "{}/server_roc.png".format(args.model_path))
    visualize.plot_confusion_matrix(client_val.value.argmax(1), client_pred.argmax(1),
                                    "{}/client_cov.png".format(args.model_path),
                                    normalize=False, title="Client Confusion Matrix")
    visualize.plot_confusion_matrix(server_val.value.argmax(1), server_pred.argmax(1),
                                    "{}/server_cov.png".format(args.model_path),
                                    normalize=False, title="Server Confusion Matrix")


def main_score():
    # mask = dataset.load_mask_eval(args.data, args.test_image)
    # pred = np.load(args.pred)
    # visualize.score_model(mask, pred)
    pass


def main_data():
    char_dict = dataset.get_character_dict()
    user_flow_df = dataset.get_user_flow_data(args.train_data)
    logger.info("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)
    print(f"domain shape {domain_tr.shape}")
    print(f"flow shape {flow_tr.shape}")
    print(f"client shape {client_tr.shape}")
    print(f"server shape {server_tr.shape}")


def main():
    if "train" in args.modes:
        main_train()
    if "hyperband" in args.modes:
        main_hyperband()
    if "test" in args.modes:
        main_test()
    if "fancy" in args.modes:
        main_visualization()
    if "score" in args.modes:
        main_score()
    if "paul" in args.modes:
        main_paul_best()
    if "data" in args.modes:
        main_data()
    if "train_new" in args.modes:
        main_new_model()


if __name__ == "__main__":
    main()