ma_cisco_malware/models/pauls_networks.py

import keras
from keras.engine import Input, Model
from keras.layers import Embedding, Conv1D, GlobalMaxPooling1D, Dense, Dropout, Activation, TimeDistributed

best_config = {
    'domain_features': 32,
    'drop_out': 0.5,
    'embedding_size': 64,
    'filter_main': 512,
    'flow_features': 3,
    'hidden_dims': 32,
    'filter_embedding': 32,
    'hidden_embedding': 32,
    'kernel_embedding': 8,
    'kernels_main': 8,
    'input_length': 40
}


def get_embedding(vocab_size, embedding_size, input_length,
                  filters, kernel_size, hidden_dims, drop_out=0.5):
    x = y = Input(shape=(input_length,))
    y = Embedding(input_dim=vocab_size, output_dim=embedding_size)(y)
    y = Conv1D(filters, kernel_size, activation='relu')(y)
    y = GlobalMaxPooling1D()(y)
    y = Dense(hidden_dims)(y)
    y = Dropout(drop_out)(y)
    y = Activation('relu')(y)
    return Model(x, y)


def get_model(cnnDropout, flow_features, domain_features, window_size, domain_length, cnn_dims, kernel_size,
              dense_dim, cnn):
    ipt_domains = Input(shape=(window_size, domain_length), name="ipt_domains")
    encoded = TimeDistributed(cnn)(ipt_domains)
    ipt_flows = Input(shape=(window_size, flow_features), name="ipt_flows")
    merged = keras.layers.concatenate([encoded, ipt_flows], -1)
    # CNN processing a small slides of flow windows
    # TODO: add more layers?
    y = Conv1D(cnn_dims,
               kernel_size,
               activation='relu',
               input_shape=(window_size, domain_features + flow_features))(merged)
    # remove temporal dimension by global max pooling
    y = GlobalMaxPooling1D()(y)
    y = Dropout(cnnDropout)(y)
    y = Dense(dense_dim, activation='relu')(y)
    y1 = Dense(2, activation='softmax', name="client")(y)
    y2 = Dense(2, activation='softmax', name="server")(y)

    return Model(inputs=[ipt_domains, ipt_flows], outputs=(y1, y2))