My master thesis project on malware detection using neural networks and multi task learning
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

41 lines
1.6 KiB

import keras
from keras.engine import Input, Model
from keras.layers import Embedding, Conv1D, GlobalMaxPooling1D, Dense, Dropout, Activation, TimeDistributed
def get_shared_cnn(vocab_size, embedding_size, input_length, filters, kernel_size,
hidden_dims, drop_out):
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_full_model(vocabSize, embeddingSize, maxLen, domainFeatures, flowFeatures,
filters, h1, h2, dropout, dense):
def get_top_cnn(cnn, numFeatures, maxLen, windowSize, domainFeatures, filters, kernel_size, cnnHiddenDims, cnnDropout):
ipt_domains = Input(shape=(windowSize, maxLen), name="ipt_domains")
encoded = TimeDistributed(cnn)(ipt_domains)
ipt_flows = Input(shape=(windowSize, numFeatures), name="ipt_flows")
merged = keras.layers.concatenate([encoded, ipt_flows], -1)
# add second cnn
y = Conv1D(filters,
input_shape=(windowSize, domainFeatures + numFeatures))(merged)
# TODO: why global pooling? -> 3D to 2D
# we use max pooling:
y = GlobalMaxPooling1D()(y)
y = Dropout(cnnDropout)(y)
y = Dense(cnnHiddenDims, 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))