ma_cisco_malware/dataset.py

199 lines
6.8 KiB
Python

# -*- coding: utf-8 -*-
import string
import numpy as np
import pandas as pd
from tqdm import tqdm
chars = dict((char, idx + 1) for (idx, char) in
enumerate(string.ascii_lowercase + string.punctuation + string.digits))
def get_character_dict():
return chars
def encode_char(c):
if c in chars:
return chars[c]
else:
return 0
encode_char = np.vectorize(encode_char)
def get_user_chunks(dataFrame, windowSize=10, overlapping=False,
maxLengthInSeconds=300):
maxMilliSeconds = maxLengthInSeconds * 1000
outDomainLists = []
outDFFrames = []
if overlapping == False:
numBlocks = int(np.ceil(float(len(dataFrame)) / float(windowSize)))
userIDs = np.arange(len(dataFrame))
for blockID in np.arange(numBlocks):
curIDs = userIDs[(blockID * windowSize):((blockID + 1) * windowSize)]
# print(curIDs)
useData = dataFrame.iloc[curIDs]
curDomains = useData['domain']
if maxLengthInSeconds != -1:
curMinMilliSeconds = np.min(useData['timeStamp']) + maxMilliSeconds
underTimeOutIDs = np.where(np.array(useData['timeStamp']) <= curMinMilliSeconds)
if len(underTimeOutIDs) != len(curIDs):
curIDs = curIDs[underTimeOutIDs]
useData = dataFrame.iloc[curIDs]
curDomains = useData['domain']
outDomainLists.append(list(curDomains))
outDFFrames.append(useData)
else:
numBlocks = len(dataFrame) + 1 - windowSize
userIDs = np.arange(len(dataFrame))
for blockID in np.arange(numBlocks):
curIDs = userIDs[blockID:blockID + windowSize]
useData = dataFrame.iloc[curIDs]
curDomains = useData['domain']
if maxLengthInSeconds != -1:
curMinMilliSeconds = np.min(useData['timeStamp']) + maxMilliSeconds
underTimeOutIDs = np.where(np.array(useData['timeStamp']) <= curMinMilliSeconds)
if len(underTimeOutIDs) != len(curIDs):
curIDs = curIDs[underTimeOutIDs]
useData = dataFrame.iloc[curIDs]
curDomains = useData['domain']
outDomainLists.append(list(curDomains))
outDFFrames.append(useData)
if len(outDomainLists[-1]) != windowSize:
outDomainLists.pop(-1)
outDFFrames.pop(-1)
return (outDomainLists, outDFFrames)
def get_domain_features(domain, vocab, max_length=40):
encoding = np.zeros((max_length,))
for j in range(np.min([len(domain), max_length])):
curCharacter = domain[-j]
if curCharacter in vocab:
encoding[j] = vocab[curCharacter]
return encoding
def get_flow_features(flow):
keys = ['duration', 'bytes_down', 'bytes_up']
features = np.zeros([len(keys), ])
for i, key in enumerate(keys):
# TODO: does it still works after exceptions occur -- default: zero!
# i wonder whether something brokes
# if there are exceptions regarding to inconsistent feature length
try:
features[i] = np.log1p(flow[key]).astype(float)
except:
pass
return features
def get_cisco_features(curDataLine, urlSIPDict):
numCiscoFeatures = 30
try:
ciscoFeatures = urlSIPDict[str(curDataLine['domain']) + str(curDataLine['server_ip'])]
# log transform
ciscoFeatures = np.log1p(ciscoFeatures).astype(float)
return ciscoFeatures.ravel()
except:
return np.zeros([numCiscoFeatures, ]).ravel()
def create_dataset_from_flows(user_flow_df, char_dict, max_len, window_size=10, use_cisco_features=False):
domains = []
features = []
print("get chunks from user data frames")
for i, user_flow in enumerate(get_flow_per_user(user_flow_df)):
(domain_windows, feature_windows) = get_user_chunks(user_flow,
windowSize=window_size,
overlapping=True,
maxLengthInSeconds=-1)
domains += domain_windows
features += feature_windows
# TODO: remove later
if i >= 10:
break
print("create training dataset")
return create_dataset_from_lists(
domains=domains, features=features, vocab=char_dict,
max_len=max_len,
use_cisco_features=use_cisco_features, urlSIPDIct=dict(),
window_size=window_size)
def create_dataset_from_lists(domains, features, vocab, max_len,
use_cisco_features=False, urlSIPDIct=dict(),
window_size=10):
"""
combines domain and feature windows to sequential training data
:param domains: list of domain windows
:param features: list of feature windows
:param vocab:
:param max_len:
:param use_cisco_features: idk
:param urlSIPDIct: idk
:param window_size: size of the flow window
:return:
"""
# TODO: check for hits vs vth consistency
# if 'hits' in dfs[0].keys():
# hits_col = 'hits'
# elif 'virusTotalHits' in dfs[0].keys():
# hits_col = 'virusTotalHits'
hits_col = "virusTotalHits"
numFlowFeatures = 3
numCiscoFeatures = 30
numFeatures = numFlowFeatures
if use_cisco_features:
numFeatures += numCiscoFeatures
sample_size = len(domains)
hits = []
names = []
servers = []
trusted_hits = []
domain_features = np.zeros((sample_size, window_size, max_len))
flow_features = np.zeros((sample_size, window_size, numFeatures))
for i in tqdm(np.arange(sample_size), miniters=10):
for j in range(window_size):
domain_features[i, j] = get_domain_features(domains[i][j], vocab, max_len)
flow_features[i, j] = get_flow_features(features[i].iloc[j])
# TODO: cisco features?
hits.append(np.max(features[i][hits_col]))
names.append(np.unique(features[i]['user_hash']))
servers.append(np.max(features[i]['serverLabel']))
trusted_hits.append(np.max(features[i]['trustedHits']))
X = [domain_features, flow_features]
return X, np.array(hits), np.array(names), np.array(servers), np.array(trusted_hits)
def discretize_label(values, threshold):
maxVal = np.max(values)
if maxVal >= threshold:
return 1.0
elif maxVal == -1:
return -1.0
elif 0 < maxVal < threshold:
return -2.0
else:
return 0.0
def get_user_flow_data():
df = pd.read_csv("data/rk_data.csv.gz")
df.drop("Unnamed: 0", 1, inplace=True)
df.set_index(keys=['user_hash'], drop=False, inplace=True)
return df
def get_flow_per_user(df):
users = df['user_hash'].unique().tolist()
for user in users:
yield df.loc[df.user_hash == user]