def getModelData(webpageIds,runID):
countermeasure = intToCountermeasure(config.COUNTERMEASURE)
traintracesofWebsite = []
targetWebpage = None
if config.DATA_SOURCE == 0:
startIndex = config.GLOVE_OPTIONS['ModelTraceNum']
endIndex = len(config.DATA_SET) - config.NUM_TESTING_TRACES
elif config.DATA_SOURCE == 1:
maxTracesPerWebsiteH = 160
startIndex = config.GLOVE_OPTIONS['ModelTraceNum']
endIndex = maxTracesPerWebsiteH - config.NUM_TESTING_TRACES
elif config.DATA_SOURCE == 2:
maxTracesPerWebsiteH = 18
startIndex = config.GLOVE_OPTIONS['ModelTraceNum']
endIndex = maxTracesPerWebsiteH - config.NUM_TESTING_TRACES
elif config.DATA_SOURCE == 3:
config.DATA_SET = config.DATA_SET_ANDROID_TOR
startIndex = config.GLOVE_OPTIONS['ModelTraceNum']
endIndex = len(config.DATA_SET) - config.NUM_TESTING_TRACES
config.PCAP_ROOT = os.path.join(config.BASE_DIR, 'pcap-logs-Android-Tor-Grouping')
seed = random.randint(startIndex, endIndex)
for webpageId in webpageIds:
if config.DATA_SOURCE == 0 or config.DATA_SOURCE == 3:
webpageTrain = Datastore.getWebpagesLL([webpageId], seed - config.GLOVE_OPTIONS['ModelTraceNum'], seed)
elif config.DATA_SOURCE == 1 or config.DATA_SOURCE == 2:
webpageTrain = Datastore.getWebpagesHerrmann([webpageId], seed - config.GLOVE_OPTIONS['ModelTraceNum'], seed)
webpageTrain = webpageTrain[0]
# print webpageTrain
# print webpageTrain.getHistogram()
if targetWebpage == None:
targetWebpage = webpageTrain
metadata = None
if config.COUNTERMEASURE in [config.DIRECT_TARGET_SAMPLING, config.WRIGHT_STYLE_MORPHING]:
metadata = countermeasure.buildMetadata(webpageTrain, targetWebpage)
i = 0
for w in [webpageTrain]:
for trace in w.getTraces():
if countermeasure:
if config.COUNTERMEASURE in [config.DIRECT_TARGET_SAMPLING, config.WRIGHT_STYLE_MORPHING]:
if w.getId() != targetWebpage.getId():
traceWithCountermeasure = countermeasure.applyCountermeasure(trace, metadata)
else:
traceWithCountermeasure = trace
else:
traceWithCountermeasure = countermeasure.applyCountermeasure(trace)
else:
traceWithCountermeasure = trace
if i == 0:
traintracesofWebsite.append(traceWithCountermeasure)
generateModel(traintracesofWebsite, runID)
targetWebpage = None
traintracesofWebsite = []
testtracesofWebsite = []
if config.CLASSIFIER == config.GLOVE_CLASSIFIER or config.CLASSIFIER == config.GLOVE_CLASSIFIER2:
getModelData(webpageIds,runID)
tempRunID = runID
for webpageId in webpageIds:
if config.DATA_SOURCE == 0 or config.DATA_SOURCE == 3:
webpageTrain = Datastore.getWebpagesLL([webpageId], seed - config.NUM_TRAINING_TRACES, seed)
webpageTest = Datastore.getWebpagesLL([webpageId], seed, seed + config.NUM_TESTING_TRACES)
elif config.DATA_SOURCE == 1 or config.DATA_SOURCE == 2:
webpageTrain = Datastore.getWebpagesHerrmann([webpageId], seed - config.NUM_TRAINING_TRACES, seed)
webpageTest = Datastore.getWebpagesHerrmann([webpageId], seed, seed + config.NUM_TESTING_TRACES)
webpageTrain = webpageTrain[0]
webpageTest = webpageTest[0]
# print webpageTrain
# print webpageTrain.getHistogram()
if targetWebpage == None:
targetWebpage = webpageTrain
preCountermeasureOverhead += webpageTrain.getBandwidth()
preCountermeasureOverhead += webpageTest.getBandwidth()
#print preCountermeasureOverhead
metadata = None
def run():
run_id, countermeasure_params, classifier_params = read_arguments()
output_filename_list = [
'results',
'k' + str(config.BUCKET_SIZE),
'c' + str(config.COUNTERMEASURE),
'd' + str(config.DATA_SOURCE),
'C' + str(config.CLASSIFIER),
'N' + str(config.TOP_N),
't' + str(config.NUM_TRAINING_TRACES),
'T' + str(config.NUM_TESTING_TRACES),
]
output_filename = os.path.join(config.OUTPUT_DIR,
'.'.join(output_filename_list))
if not os.path.exists(config.CACHE_DIR):
os.mkdir(config.CACHE_DIR)
if not os.path.exists(output_filename + '.output'):
banner = [
'accuracy', 'overhead', 'timeElapsedTotal', 'timeElapsedClassifier'
]
f = open(output_filename + '.output', 'w')
f.write(','.join(banner))
f.close()
if not os.path.exists(output_filename + '.debug'):
f = open(output_filename + '.debug', 'w')
f.close()
# Data-set Selection
training_set_size = config.NUM_TRAINING_TRACES
testing_set_size = config.NUM_TESTING_TRACES
if config.DATA_SOURCE == 0:
dataset_size = len(config.DATA_SET)
start_index = config.NUM_TRAINING_TRACES
end_index = len(config.DATA_SET) - config.NUM_TESTING_TRACES
elif config.DATA_SOURCE == 1:
dataset_size = 160
max_traces_per_website_h = 160
start_index = config.NUM_TRAINING_TRACES
end_index = max_traces_per_website_h - config.NUM_TESTING_TRACES
elif config.DATA_SOURCE == 2:
dataset_size = 18
max_traces_per_website_h = 18
start_index = config.NUM_TRAINING_TRACES
end_index = max_traces_per_website_h - config.NUM_TESTING_TRACES
else:
error('Invalid data-source id:', config.DATA_SOURCE)
return 3
# Checking Training-set and Test-set Sizes
info('|dataset|={}\t|training-set|={}, |testing-set|={}'.format(
dataset_size, training_set_size, testing_set_size))
if training_set_size + testing_set_size > dataset_size:
print('[ERROR] t+T is larger than data-set size!')
print(
'\tThe data-set is divided into two parts: Training set (t) and Testing set (T), so t+T must be '
)
print('\tless than or equal to the total number of data in data-set.')
sys.exit(4)
# Selecting Algorithms
classifier = int_to_classifier(config.CLASSIFIER)
countermeasure = int_to_countermeasure(config.COUNTERMEASURE)
if issubclass(countermeasure, CounterMeasure):
countermeasure.initialize()
countermeasure = countermeasure() # also instantiating
new_style_cm = True
else:
new_style_cm = False
countermeasure_params = countermeasure_params.split(',')
for p in countermeasure_params:
if not p or not p.strip():
continue
try:
attr, val = p.strip().split('=', 1)
except ValueError:
error('Invalid parameter:', p)
return 3
try:
val = int(val)
except ValueError:
pass
if new_style_cm:
countermeasure.set_param(attr, val)
else:
setattr(countermeasure, attr, val)
# Run
for run_index in range(config.NUM_TRIALS):
run_start_time = time.time()
print('Run #{}'.format(run_index))
# Select a sample of size k from websites 1..N
webpage_ids = range(0, config.TOP_N - 1)
random.shuffle(webpage_ids)
webpage_ids = webpage_ids[0:config.BUCKET_SIZE]
seed = random.randint(start_index, end_index)
info('selected webpages:', webpage_ids)
training_set = []
testing_set = []
target_webpage = None
actual_bandwidth = 0
modified_bandwidth = 0
actual_timing = 0
modified_timing = 0
for page_id in webpage_ids:
print('.', end='')
sys.stdout.flush()
# Sampling From Data-source
if config.DATA_SOURCE == 0:
webpage_train = Datastore.getWebpagesLL(
[page_id], seed - config.NUM_TRAINING_TRACES, seed)
webpage_test = Datastore.getWebpagesLL(
[page_id], seed, seed + config.NUM_TESTING_TRACES)
elif config.DATA_SOURCE in [1, 2]:
webpage_train = Datastore.getWebpagesHerrmann(
[page_id], seed - config.NUM_TRAINING_TRACES, seed)
webpage_test = Datastore.getWebpagesHerrmann(
[page_id], seed, seed + config.NUM_TESTING_TRACES)
else:
error('Invalid data-source id:', config.DATA_SOURCE)
return 3
# Selecting Targets
webpage_train = webpage_train[0]
webpage_test = webpage_test[0]
if target_webpage is None:
target_webpage = webpage_train
print(webpage_test, webpage_train)
# Accounting
actual_bandwidth += webpage_train.getBandwidth()
actual_bandwidth += webpage_test.getBandwidth()
# Train Countermeasure
metadata = None
if new_style_cm:
countermeasure.train(src_page=webpage_train,
target_page=target_webpage)
else:
if countermeasure in [
DirectTargetSampling, WrightStyleMorphing
]:
metadata = countermeasure.buildMetadata(
webpage_train, target_webpage)
# Applying Countermeasure (and feeding data to classifier)
for i, w in enumerate([webpage_train, webpage_test]):
for trace in w.getTraces():
actual_timing += trace.get_total_time()
# print(trace.get_total_time(), '-', end='')
if countermeasure:
if new_style_cm:
modified_trace = countermeasure.apply_to_trace(
trace)
else:
if countermeasure in [
DirectTargetSampling, WrightStyleMorphing
]:
if w.getId() != target_webpage.getId():
modified_trace = countermeasure.applyCountermeasure(
trace, metadata)
else:
modified_trace = trace
else:
modified_trace = countermeasure.applyCountermeasure(
trace)
else:
modified_trace = trace
# Overhead Accounting
modified_bandwidth += modified_trace.getBandwidth()
modified_timing += modified_trace.get_total_time()
# print(modified_trace.get_total_time())
instance = classifier.traceToInstance(modified_trace)
if instance:
if i == 0: # train-page
training_set.append(instance)
elif i == 1: # test-page
testing_set.append(instance)
# Classification
print('')
classification_start_time = time.time()
cl = classifier.classify(run_id, training_set, testing_set)
run_end_time = time.time()
run_total_time = run_end_time - run_start_time
classification_total_time = run_end_time - classification_start_time
report_summary(cl,
output_filename=output_filename,
classifier=classifier,
countermeasure=countermeasure)
return 0
postCountermeasureOverhead = 0
classifier = intToClassifier(config.CLASSIFIER)
countermeasure = intToCountermeasure(config.COUNTERMEASURE)
trainingSet = []
testingSet = []
targetWebpage = None
for webpageId in webpageIds:
if config.DATA_SOURCE == 0:
webpageTrain = Datastore.getWebpagesLL( [webpageId], seed-config.NUM_TRAINING_TRACES, seed )
webpageTest = Datastore.getWebpagesLL( [webpageId], seed, seed+config.NUM_TESTING_TRACES )
elif config.DATA_SOURCE == 1 or config.DATA_SOURCE == 2:
webpageTrain = Datastore.getWebpagesHerrmann( [webpageId], seed-config.NUM_TRAINING_TRACES, seed )
webpageTest = Datastore.getWebpagesHerrmann( [webpageId], seed, seed+config.NUM_TESTING_TRACES )
webpageTrain = webpageTrain[0]
webpageTest = webpageTest[0]
if targetWebpage == None:
targetWebpage = webpageTrain
preCountermeasureOverhead += webpageTrain.getBandwidth()
preCountermeasureOverhead += webpageTest.getBandwidth()
metadata = None
if config.COUNTERMEASURE in [config.DIRECT_TARGET_SAMPLING, config.WRIGHT_STYLE_MORPHING]:
metadata = countermeasure.buildMetadata( webpageTrain, targetWebpage )
def run():
run_id, countermeasure_params, classifier_params = read_arguments()
output_filename_list = [
'results',
'k' + str(config.BUCKET_SIZE),
'c' + str(config.COUNTERMEASURE),
'd' + str(config.DATA_SOURCE),
'C' + str(config.CLASSIFIER),
'N' + str(config.TOP_N),
't' + str(config.NUM_TRAINING_TRACES),
'T' + str(config.NUM_TESTING_TRACES),
]
output_filename = os.path.join(config.OUTPUT_DIR, '.'.join(output_filename_list))
if not os.path.exists(config.CACHE_DIR):
os.mkdir(config.CACHE_DIR)
if not os.path.exists(output_filename + '.output'):
banner = ['accuracy', 'overhead', 'timeElapsedTotal', 'timeElapsedClassifier']
f = open(output_filename + '.output', 'w')
f.write(','.join(banner))
f.close()
if not os.path.exists(output_filename + '.debug'):
f = open(output_filename + '.debug', 'w')
f.close()
# Data-set Selection
training_set_size = config.NUM_TRAINING_TRACES
testing_set_size = config.NUM_TESTING_TRACES
if config.DATA_SOURCE == 0:
dataset_size = len(config.DATA_SET)
start_index = config.NUM_TRAINING_TRACES
end_index = len(config.DATA_SET) - config.NUM_TESTING_TRACES
elif config.DATA_SOURCE == 1:
dataset_size = 160
max_traces_per_website_h = 160
start_index = config.NUM_TRAINING_TRACES
end_index = max_traces_per_website_h - config.NUM_TESTING_TRACES
elif config.DATA_SOURCE == 2:
dataset_size = 18
max_traces_per_website_h = 18
start_index = config.NUM_TRAINING_TRACES
end_index = max_traces_per_website_h - config.NUM_TESTING_TRACES
else:
error('Invalid data-source id:', config.DATA_SOURCE)
return 3
# Checking Training-set and Test-set Sizes
info('|dataset|={}\t|training-set|={}, |testing-set|={}'.format(dataset_size, training_set_size, testing_set_size))
if training_set_size + testing_set_size > dataset_size:
print('[ERROR] t+T is larger than data-set size!')
print('\tThe data-set is divided into two parts: Training set (t) and Testing set (T), so t+T must be ')
print('\tless than or equal to the total number of data in data-set.')
sys.exit(4)
# Selecting Algorithms
classifier = int_to_classifier(config.CLASSIFIER)
countermeasure = int_to_countermeasure(config.COUNTERMEASURE)
if issubclass(countermeasure, CounterMeasure):
countermeasure.initialize()
countermeasure = countermeasure() # also instantiating
new_style_cm = True
else:
new_style_cm = False
countermeasure_params = countermeasure_params.split(',')
for p in countermeasure_params:
if not p or not p.strip():
continue
try:
attr, val = p.strip().split('=', 1)
except ValueError:
error('Invalid parameter:', p)
return 3
try:
val = int(val)
except ValueError:
pass
if new_style_cm:
countermeasure.set_param(attr, val)
else:
setattr(countermeasure, attr, val)
# Run
for run_index in range(config.NUM_TRIALS):
run_start_time = time.time()
print('Run #{}'.format(run_index))
# Select a sample of size k from websites 1..N
webpage_ids = range(0, config.TOP_N - 1)
random.shuffle(webpage_ids)
webpage_ids = webpage_ids[0:config.BUCKET_SIZE]
seed = random.randint(start_index, end_index)
info('selected webpages:', webpage_ids)
training_set = []
testing_set = []
target_webpage = None
actual_bandwidth = 0
modified_bandwidth = 0
actual_timing = 0
modified_timing = 0
for page_id in webpage_ids:
print('.', end='')
sys.stdout.flush()
# Sampling From Data-source
if config.DATA_SOURCE == 0:
webpage_train = Datastore.getWebpagesLL([page_id], seed - config.NUM_TRAINING_TRACES, seed)
webpage_test = Datastore.getWebpagesLL([page_id], seed, seed + config.NUM_TESTING_TRACES)
elif config.DATA_SOURCE in [1, 2]:
webpage_train = Datastore.getWebpagesHerrmann([page_id], seed - config.NUM_TRAINING_TRACES, seed)
webpage_test = Datastore.getWebpagesHerrmann([page_id], seed, seed + config.NUM_TESTING_TRACES)
else:
error('Invalid data-source id:', config.DATA_SOURCE)
return 3
# Selecting Targets
webpage_train = webpage_train[0]
webpage_test = webpage_test[0]
if target_webpage is None:
target_webpage = webpage_train
print(webpage_test, webpage_train)
# Accounting
actual_bandwidth += webpage_train.getBandwidth()
actual_bandwidth += webpage_test.getBandwidth()
# Train Countermeasure
metadata = None
if new_style_cm:
countermeasure.train(src_page=webpage_train, target_page=target_webpage)
else:
if countermeasure in [DirectTargetSampling, WrightStyleMorphing]:
metadata = countermeasure.buildMetadata(webpage_train, target_webpage)
# Applying Countermeasure (and feeding data to classifier)
for i, w in enumerate([webpage_train, webpage_test]):
for trace in w.getTraces():
actual_timing += trace.get_total_time()
# print(trace.get_total_time(), '-', end='')
if countermeasure:
if new_style_cm:
modified_trace = countermeasure.apply_to_trace(trace)
else:
if countermeasure in [DirectTargetSampling, WrightStyleMorphing]:
if w.getId() != target_webpage.getId():
modified_trace = countermeasure.applyCountermeasure(trace, metadata)
else:
modified_trace = trace
else:
modified_trace = countermeasure.applyCountermeasure(trace)
else:
modified_trace = trace
# Overhead Accounting
modified_bandwidth += modified_trace.getBandwidth()
modified_timing += modified_trace.get_total_time()
# print(modified_trace.get_total_time())
instance = classifier.traceToInstance(modified_trace)
if instance:
if i == 0: # train-page
training_set.append(instance)
elif i == 1: # test-page
testing_set.append(instance)
# Classification
print('')
classification_start_time = time.time()
cl = classifier.classify(run_id, training_set, testing_set)
run_end_time = time.time()
run_total_time = run_end_time - run_start_time
classification_total_time = run_end_time - classification_start_time
report_summary(cl, output_filename=output_filename,
classifier=classifier, countermeasure=countermeasure)
return 0
