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 CSVLogger, EarlyStopping, LambdaCallback, ModelCheckpoint
from keras.models import Model, load_model

import arguments
import dataset
import hyperband
import models
# create logger
import visualize
from arguments import get_model_args
from utils import exists_or_make_path, get_custom_class_weights

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)

# default parameter
PARAMS = {
    "type": args.model_type,
    "depth": args.model_depth,
    # "batch_size": 64,
    "window_size": args.window,
    "domain_length": args.domain_length,
    "flow_features": 3,
    #
    'dropout': 0.5,  # currently fix
    'domain_features': args.domain_embedding,
    'embedding_size': args.embedding,
    'flow_features': 3,
    'filter_embedding': args.filter_embedding,
    'dense_embedding': args.dense_embedding,
    'kernel_embedding': args.kernel_embedding,
    'filter_main': args.filter_main,
    'dense_main': args.dense_main,
    'kernel_main': args.kernel_main,
    'input_length': 40,
    'model_output': args.model_output
}


def create_model(model, output_type):
    if output_type == "both":
        return Model(inputs=[model.in_domains, model.in_flows], outputs=(model.out_client, model.out_server))
    elif output_type == "client":
        return Model(inputs=[model.in_domains, model.in_flows], outputs=(model.out_client,))
    else:
        raise Exception("unknown model output")


def main_paul_best():
    pauls_best_params = models.pauls_networks.best_config
    main_train(pauls_best_params)


def main_hyperband():
    params = {
        # static params
        "type": ["paul"],
        "batch_size": [args.batch_size],
        "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, name_tr, client_tr, server_tr = dataset.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 main_train(param=None):
    logger.info(f"Create model path {args.model_path}")
    exists_or_make_path(args.model_path)
    logger.info(f"Use command line arguments: {args}")

    domain_tr, flow_tr, name_tr, client_tr, server_windows_tr = dataset.load_or_generate_h5data(args.train_h5data,
                                                                                                args.train_data,
                                                                                                args.domain_length,
                                                                                                args.window)
    logger.info("define callbacks")
    callbacks = []
    callbacks.append(ModelCheckpoint(filepath=args.clf_model,
                                     monitor='loss',
                                     verbose=False,
                                     save_best_only=True))
    callbacks.append(CSVLogger(args.train_log))
    logger.info(f"Use early stopping: {args.stop_early}")
    if args.stop_early:
        callbacks.append(EarlyStopping(monitor='val_loss',
                                       patience=5,
                                       verbose=False))
    custom_metrics = models.get_metric_functions()

    server_tr = np.max(server_windows_tr, axis=1)

    if args.class_weights:
        logger.info("class weights: compute custom weights")
        custom_class_weights = get_custom_class_weights(client_tr.value, server_tr)
        logger.info(custom_class_weights)
    else:
        logger.info("class weights: set default")
        custom_class_weights = None

    if not param:
        param = PARAMS
    logger.info(f"Generator model with params: {param}")
    embedding, model, new_model = models.get_models_by_params(param)

    callbacks.append(LambdaCallback(
            on_epoch_end=lambda epoch, logs: embedding.save(args.embedding_model))
    )

    model = create_model(model, args.model_output)
    new_model = create_model(new_model, args.model_output)

    if args.model_type in ("inter", "staggered"):
        server_tr = np.expand_dims(server_windows_tr, 2)
        model = new_model

    features = {"ipt_domains": domain_tr.value, "ipt_flows": flow_tr.value}
    if args.model_output == "both":
        labels = {"client": client_tr.value, "server": server_tr}
        loss_weights = {"client": 1.0, "server": 1.0}
    elif args.model_output == "client":
        labels = {"client": client_tr.value}
        loss_weights = {"client": 1.0}
    elif args.model_output == "server":
        labels = {"server": server_tr}
        loss_weights = {"server": 1.0}
    else:
        raise ValueError("unknown model output")

    logger.info(f"select model: {args.model_type}")
    if args.model_type == "staggered":
        logger.info("compile and pre-train server model")
        logger.info(model.get_config())

        model.compile(optimizer='adam',
                      loss='binary_crossentropy',
                      loss_weights={"client": 0.0, "server": 1.0},
                      metrics=['accuracy'] + custom_metrics)

        model.fit(features, labels,
                  batch_size=args.batch_size,
                  epochs=args.epochs,
                  class_weight=custom_class_weights)
    
        logger.info("fix server model")
        model.get_layer("domain_cnn").trainable = False
        model.get_layer("dense_server").trainable = False
        model.get_layer("server").trainable = False
        loss_weights = {"client": 1.0, "server": 0.0}

    logger.info("compile and train model")
    embedding.summary()
    logger.info(model.get_config())
    model.compile(optimizer='adam',
                  loss='binary_crossentropy',
                  loss_weights=loss_weights,
                  metrics=['accuracy'] + custom_metrics)

    model.summary()
    model.fit(features, labels,
              batch_size=args.batch_size,
              epochs=args.epochs,
              callbacks=callbacks,
              class_weight=custom_class_weights)


def main_test():
    logger.info("start test: load data")
    domain_val, flow_val, _, _, _, _ = dataset.load_or_generate_raw_h5data(args.test_h5data,
                                                                           args.test_data,
                                                                           args.domain_length,
                                                                           args.window)
    domain_encs, _ = dataset.load_or_generate_domains(args.test_data, args.domain_length)
    
    for model_args in get_model_args(args):
        results = {}
        logger.info(f"process model {model_args['model_path']}")
        clf_model = load_model(model_args["clf_model"], custom_objects=models.get_metrics())

        pred = clf_model.predict([domain_val, flow_val],
                                 batch_size=args.batch_size,
                                 verbose=1)

        if args.model_output == "both":
            c_pred, s_pred = pred
            results["client_pred"] = c_pred
            results["server_pred"] = s_pred
        elif args.model_output == "client":
            results["client_pred"] = pred
        else:
            results["server_pred"] = pred

        embd_model = load_model(model_args["embedding_model"], custom_objects=models.get_metrics())
        domain_embeddings = embd_model.predict(domain_encs, batch_size=args.batch_size, verbose=1)
        results["domain_embds"] = domain_embeddings

        dataset.save_predictions(model_args["model_path"], results)


def main_visualization():
    _, _, name_val, hits_vt, hits_trusted, server_val = dataset.load_or_generate_raw_h5data(args.test_h5data,
                                                                                            args.test_data,
                                                                                            args.domain_length,
                                                                                            args.window)
    
    results = dataset.load_predictions(args.model_path)
    df = pd.DataFrame(data={
        "names": name_val, "client_pred": results["client_pred"].flatten(),
        "hits_vt": hits_vt, "hits_trusted": hits_trusted
    })
    df["client_val"] = np.logical_or(df.hits_vt == 1.0, df.hits_trusted >= 3)
    df_user = df.groupby(df.names).max()

    paul = dataset.load_predictions("results/paul/")
    df_paul = pd.DataFrame(data={
        "names": paul["testNames"].flatten(), "client_pred": paul["testScores"].flatten(),
        "hits_vt": paul["testLabel"].flatten(), "hits_trusted": paul["testHits"].flatten()
    })
    df_paul["client_val"] = np.logical_or(df_paul.hits_vt == 1.0, df_paul.hits_trusted >= 3)
    df_paul_user = df_paul.groupby(df_paul.names).max()
    
    logger.info("plot model")
    model = load_model(args.clf_model, custom_objects=models.get_metrics())
    visualize.plot_model_as(model, os.path.join(args.model_path, "model.png"))

    # logger.info("plot training curve")
    # logs = pd.read_csv(args.train_log)
    # if "acc" in logs.keys():
    #     visualize.plot_training_curve(logs, "", "{}/client_train.png".format(args.model_path))
    # elif "client_acc" in logs.keys() and "server_acc" in logs.keys():
    #     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))
    # else:
    #     logger.warning("Error while plotting training curves")
    
    logger.info("plot pr curve")
    visualize.plot_clf()
    visualize.plot_precision_recall(df.client_val.as_matrix(), df.client_pred.as_matrix(), args.model_name)
    visualize.plot_precision_recall(df_paul.client_val.as_matrix(), df_paul.client_pred.as_matrix(), "paul")
    visualize.plot_legend()
    visualize.plot_save("{}/window_client_prc.png".format(args.model_path))
    
    logger.info("plot roc curve")
    visualize.plot_clf()
    visualize.plot_roc_curve(df.client_val.as_matrix(), df.client_pred.as_matrix(), args.model_name)
    visualize.plot_roc_curve(df_paul.client_val.as_matrix(), df_paul.client_pred.as_matrix(), "paul")
    visualize.plot_legend()
    visualize.plot_save("{}/window_client_roc.png".format(args.model_path))
    
    visualize.plot_clf()
    visualize.plot_precision_recall(df_user.client_val.as_matrix(), df_user.client_pred.as_matrix(), args.model_name)
    visualize.plot_precision_recall(df_paul_user.client_val.as_matrix(), df_paul_user.client_pred.as_matrix(), "paul")
    visualize.plot_legend()
    visualize.plot_save("{}/user_client_prc.png".format(args.model_path))
    
    visualize.plot_clf()
    visualize.plot_roc_curve(df_user.client_val.as_matrix(), df_user.client_pred.as_matrix(), args.model_name)
    visualize.plot_roc_curve(df_paul_user.client_val.as_matrix(), df_paul_user.client_pred.as_matrix(), "paul")
    visualize.plot_legend()
    visualize.plot_save("{}/user_client_roc.png".format(args.model_path))
    # absolute values
    visualize.plot_confusion_matrix(df.client_val.as_matrix(), df.client_pred.as_matrix().round(),
                                    "{}/client_cov.png".format(args.model_path),
                                    normalize=False, title="Client Confusion Matrix")
    visualize.plot_confusion_matrix(df_user.client_val.as_matrix(), df_user.client_pred.as_matrix().round(),
                                    "{}/user_cov.png".format(args.model_path),
                                    normalize=False, title="User Confusion Matrix")
    # normalized
    visualize.plot_confusion_matrix(df.client_val.as_matrix(), df.client_pred.as_matrix().round(),
                                    "{}/client_cov_norm.png".format(args.model_path),
                                    normalize=True, title="Client Confusion Matrix")
    visualize.plot_confusion_matrix(df_user.client_val.as_matrix(), df_user.client_pred.as_matrix().round(),
                                    "{}/user_cov_norm.png".format(args.model_path),
                                    normalize=True, title="User Confusion Matrix")
    logger.info("visualize embedding")
    domain_encs, labels = dataset.load_or_generate_domains(args.test_data, args.domain_length)
    domain_embedding = results["domain_embds"]
    visualize.plot_embedding(domain_embedding, labels, path="{}/embd_svd.png".format(args.model_path), method="svd")
    visualize.plot_embedding(domain_embedding, labels, path="{}/embd_tsne.png".format(args.model_path), method="tsne")


def plot_embedding():
    logger.info("visualize embedding")
    results = dataset.load_predictions(args.model_path)
    domain_encs, labels = dataset.load_or_generate_domains(args.test_data, args.domain_length)
    domain_embedding = results["domain_embds"]
    visualize.plot_embedding(domain_embedding, labels, path="{}/embd_svd.png".format(args.model_path), method="svd")
    visualize.plot_embedding(domain_embedding, labels, path="{}/embd_tsne.png".format(args.model_path), method="tsne")


def main_visualize_all():
    _, _, name_val, hits_vt, hits_trusted, server_val = dataset.load_or_generate_raw_h5data(args.test_h5data,
                                                                                            args.test_data,
                                                                                            args.domain_length,
                                                                                            args.window)
    
    def load_df(path):
        res = dataset.load_predictions(path)
        res = pd.DataFrame(data={
            "names": name_val, "client_pred": res["client_pred"].flatten(),
            "hits_vt": hits_vt, "hits_trusted": hits_trusted
        })
        res["client_val"] = np.logical_or(res.hits_vt == 1.0, res.hits_trusted >= 3)
        return res

    paul = dataset.load_predictions("results/paul/")
    df_paul = pd.DataFrame(data={
        "names": paul["testNames"].flatten(), "client_pred": paul["testScores"].flatten(),
        "hits_vt": paul["testLabel"].flatten(), "hits_trusted": paul["testHits"].flatten()
    })
    df_paul["client_val"] = np.logical_or(df_paul.hits_vt == 1.0, df_paul.hits_trusted >= 3)
    df_paul_user = df_paul.groupby(df_paul.names).max()
    
    logger.info("plot pr curves")
    visualize.plot_clf()
    for model_args in get_model_args(args):
        df = load_df(model_args["model_path"])
        visualize.plot_precision_recall(df.client_val.as_matrix(), df.client_pred.as_matrix(), model_args["model_name"])
    visualize.plot_precision_recall(df_paul.client_val.as_matrix(), df_paul.client_pred.as_matrix(), "paul")
    visualize.plot_legend()
    visualize.plot_save(f"{args.output_prefix}_window_client_prc.png")
    
    logger.info("plot roc curves")
    visualize.plot_clf()
    for model_args in get_model_args(args):
        df = load_df(model_args["model_path"])
        visualize.plot_roc_curve(df.client_val.as_matrix(), df.client_pred.as_matrix(), model_args["model_name"])
    visualize.plot_roc_curve(df_paul.client_val.as_matrix(), df_paul.client_pred.as_matrix(), "paul")
    visualize.plot_legend()
    visualize.plot_save(f"{args.output_prefix}_window_client_roc.png")
    
    logger.info("plot user pr curves")
    visualize.plot_clf()
    for model_args in get_model_args(args):
        df = load_df(model_args["model_path"])
        df = df.groupby(df.names).max()
        visualize.plot_precision_recall(df.client_val.as_matrix(), df.client_pred.as_matrix(), model_args["model_name"])
    visualize.plot_precision_recall(df_paul_user.client_val.as_matrix(), df_paul_user.client_pred.as_matrix(), "paul")
    visualize.plot_legend()
    visualize.plot_save(f"{args.output_prefix}_user_client_prc.png")
    
    logger.info("plot user roc curves")
    visualize.plot_clf()
    for model_args in get_model_args(args):
        df = load_df(model_args["model_path"])
        df = df.groupby(df.names).max()
        visualize.plot_roc_curve(df.client_val.as_matrix(), df.client_pred.as_matrix(), model_args["model_name"])
    visualize.plot_roc_curve(df_paul_user.client_val.as_matrix(), df_paul_user.client_pred.as_matrix(), "paul")
    visualize.plot_legend()
    visualize.plot_save(f"{args.output_prefix}_user_client_roc.png")


def main():
    if "train" == args.mode:
        main_train()
    if "hyperband" == args.mode:
        main_hyperband()
    if "test" == args.mode:
        main_test()
    if "fancy" == args.mode:
        main_visualization()
    if "all_fancy" == args.mode:
        main_visualize_all()
    if "embd" == args.mode:
        plot_embedding()
    if "paul" == args.mode:
        main_paul_best()


if __name__ == "__main__":
    main()