def run_linear_open_experiment(self, iterations=10, save=False):
"""
Train a classifier on test data, obtain the best combination of
parameters through a grid search cross-validation and test the
classifier using a open-world split of the dataset. The results
from the number of iterations are saved as pz files.
:param iterations: number of runs (training/testing)
:save: save predictions and labels if True
"""
self.true_labels = np.array([])
self.predictions = np.array([])
for i in xrange(iterations):
self.randomize_dataset_open_world()
clf = GridSearchCV(svm.LinearSVC(), {'C': np.logspace(-3, 3, 7)})
clf.fit(self.X_train, self.Y_train)
out = clf.best_estimator_.decision_function(self.X_test)
classes = clf.best_estimator_.classes_
for scores in out:
m = np.max(scores)
if (abs(m / scores[:][:]) < 0.5).any():
self.predictions = np.append(self.predictions, 99)
else:
p = classes[np.where(scores == m)]
self.predictions = np.append(self.predictions, p)
self.true_labels = np.append(self.true_labels, self.Y_test)
if save:
pz.save(self.predictions, "mca_predictions_open.pz")
pz.save(self.true_labels, "mca_true_labels_open.pz")
def run_linear_open_experiment(self, iterations=10, save=False):
"""
Train a classifier on test data, obtain the best combination of
parameters through a grid search cross-validation and test the
classifier using a open-world split of the dataset. The results
from the number of iterations are saved as pz files.
:param iterations: number of runs (training/testing)
:save: save predictions and labels if True
"""
self.true_labels = np.array([])
self.predictions = np.array([])
for i in xrange(iterations):
self.randomize_dataset_open_world()
clf = GridSearchCV(svm.LinearSVC(), {'C': np.logspace(-3, 3, 7)})
clf.fit(self.X_train, self.Y_train)
out = clf.best_estimator_.decision_function(self.X_test)
classes = clf.best_estimator_.classes_
for scores in out:
m = np.max(scores)
if (abs(m/scores[:][:]) < 0.5).any():
self.predictions = np.append(self.predictions, 99)
else:
p = classes[np.where(scores==m)]
self.predictions = np.append(self.predictions, p)
self.true_labels = np.append(self.true_labels, self.Y_test)
if save:
pz.save(self.predictions, "mca_predictions_open.pz")
pz.save(self.true_labels, "mca_true_labels_open.pz")
def run_linear_experiment(self, rocs_filename, iterations=10):
"""
Run a classification experiment by running several iterations.
In each iteration data is randomized, a linear svm classifier
is trained and evaluated using cross-validation over a the
cost parameter in the range np.logspace(-3, 3, 7). The best
classifier is used for testing and a ROC curve is computed
and saved as property and locally.
:param rocs_filename: the file to save all rocs computed
:param iterations: number of runs (training/testing)
"""
for i in xrange(iterations):
print "[*] Iteration {0}".format(i)
print "[*] Randomizing dataset..."
self.randomize_dataset()
clf = GridSearchCV(svm.LinearSVC(), {'C': np.logspace(-3, 3, 7)})
print "[*] Training..."
clf.fit(self.X_train, self.Y_train)
out = clf.best_estimator_.decision_function(self.X_test)
print "[*] Testing..."
roc = eval.compute_roc(np.float32(out.flatten()),
np.float32(self.Y_test))
self.rocs.append(roc)
print "[*] ROC saved."
pz.save(self.rocs, rocs_filename)
def run_linear_experiment(self, rocs_filename, iterations=10):
"""
Run a classification experiment by running several iterations.
In each iteration data is randomized, a linear svm classifier
is trained and evaluated using cross-validation over a the
cost parameter in the range np.logspace(-3, 3, 7). The best
classifier is used for testing and a ROC curve is computed
and saved as property and locally.
:param rocs_filename: the file to save all rocs computed
:param iterations: number of runs (training/testing)
"""
for i in xrange(iterations):
print "[*] Iteration {0}".format(i)
print "[*] Randomizing dataset..."
self.randomize_dataset()
clf = GridSearchCV(svm.LinearSVC(), {'C': np.logspace(-3, 3, 7)})
print "[*] Training..."
clf.fit(self.X_train, self.Y_train)
out = clf.best_estimator_.decision_function(self.X_test)
print "[*] Testing..."
roc = eval.compute_roc(np.float32(out.flatten()),
np.float32(self.Y_test))
self.rocs.append(roc)
print "[*] ROC saved."
pz.save(self.rocs, rocs_filename)
def process_dir(read_dir, out_dir, mode='FCG'):
""" Convert a series of APK into graph objects. Load all
APKs in a dir subtree and create graph objects that are pickled
for later processing and learning.
"""
sys.setrecursionlimit(100000)
files = []
# check if pdg doesnt exist yet and mark the file to be processed
for dirName, subdirList, fileList in os.walk(read_dir):
for f in fileList:
files.append(os.path.join(dirName, f))
# set up progress bar
print "\nProcessing {} APK files in dir {}".format(len(files), read_dir)
widgets = ['Building graphs: ',
Percentage(), ' ',
Bar(marker='#', left='[', right=']'),
' ', ETA(), ' ']
pbar = ProgressBar(widgets=widgets, maxval=len(files))
pbar.start()
progress = 0
# loop through .apk files and save them in .pdg.pz format
for f in files:
f = os.path.realpath(f)
print '[] Loading {0}'.format(f)
try:
if mode is 'FCG':
graph = FCG(f)
elif mode is 'PDG':
graph = PDG(f)
# if an exception happens, save the .apk in the corresponding dir
except Exception as e:
err = e.__class__.__name__
err_dir = err + "/"
d = os.path.join(read_dir, err_dir)
if not os.path.exists(d):
os.makedirs(d)
cmd = "cp {} {}".format(f, d)
os.system(cmd)
print "[*] {} error loading {}".format(err, f)
continue
h = get_sha256(f)
if out_dir:
out = out_dir
else:
out = read_dir
fnx = os.path.join(out, "{}.pz".format(h))
pz.save(graph.g, fnx)
print "[*] Saved {}\n".format(fnx)
progress += 1
pbar.update(progress)
pbar.finish()
print "Done."
def run_linear_closed_experiment(self, iterations=10, save=False):
"""
Train a classifier on test data, obtain the best combination of
parameters through a grid search cross-validation and test the
classifier using a closed-world split of the dataset. The results
from the number of iterations are saved as pz files.
:param iterations: number of runs (training/testing)
:save: save predictions and labels if True
"""
self.true_labels = np.array([])
self.predictions = np.array([])
for i in xrange(iterations):
self.randomize_dataset_closed_world()
clf = GridSearchCV(svm.LinearSVC(), {'C': np.logspace(-3, 3, 7)})
clf.fit(self.X_train, self.Y_train)
out = clf.best_estimator_.predict(self.X_test)
self.predictions = np.append(self.predictions, out)
self.true_labels = np.append(self.true_labels, self.Y_test)
if save:
pz.save(self.predictions, "mca_predictions_closed.pz")
pz.save(self.true_labels, "mca_true_labels_closed.pz")
def run_linear_closed_experiment(self, iterations=10, save=False):
"""
Train a classifier on test data, obtain the best combination of
parameters through a grid search cross-validation and test the
classifier using a closed-world split of the dataset. The results
from the number of iterations are saved as pz files.
:param iterations: number of runs (training/testing)
:save: save predictions and labels if True
"""
self.true_labels = np.array([])
self.predictions = np.array([])
for i in xrange(iterations):
self.randomize_dataset_closed_world()
clf = GridSearchCV(svm.LinearSVC(), {'C': np.logspace(-3, 3, 7)})
clf.fit(self.X_train, self.Y_train)
out = clf.best_estimator_.predict(self.X_test)
self.predictions = np.append(self.predictions, out)
self.true_labels = np.append(self.true_labels, self.Y_test)
if save:
pz.save(self.predictions, "mca_predictions_closed.pz")
pz.save(self.true_labels, "mca_true_labels_closed.pz")
def save_data(self):
""" Store pz objects for the data matrix, the labels and
the name of the original samples so that they can be used
in a new experiment without the need to extract all
features again
"""
print "[*] Saving labels, data matrix and file names..."
pz.save(self.X, "X.pz")
pz.save(self.Y, "Y.pz")
pz.save(self.fnames, "fnames.pz")
def save_data(self):
""" Store pz objects for the data matrix, the labels and
the name of the original samples so that they can be used
in a new experiment without the need to extract all
features again
"""
print "[*] Saving labels, data matrix and file names..."
pz.save(self.X, "X.pz")
pz.save(self.Y, "Y.pz")
pz.save(self.fnames, "fnames.pz")
