diff --git a/research/differential_privacy/pate/ICLR2018/download.py b/research/differential_privacy/pate/ICLR2018/download.py index 022df1d..33a4784 100644 --- a/research/differential_privacy/pate/ICLR2018/download.py +++ b/research/differential_privacy/pate/ICLR2018/download.py @@ -32,7 +32,26 @@ def download(): tar_filename, _ = urllib.request.urlretrieve(FILE_URI) print('Unpacking ' + tar_filename) with tarfile.open(tar_filename, "r:gz") as tar: - tar.extractall(DATA_DIR) + def is_within_directory(directory, target): + + abs_directory = os.path.abspath(directory) + abs_target = os.path.abspath(target) + + prefix = os.path.commonprefix([abs_directory, abs_target]) + + return prefix == abs_directory + + def safe_extract(tar, path=".", members=None, *, numeric_owner=False): + + for member in tar.getmembers(): + member_path = os.path.join(path, member.name) + if not is_within_directory(path, member_path): + raise Exception("Attempted Path Traversal in Tar File") + + tar.extractall(path, members, numeric_owner=numeric_owner) + + + safe_extract(tar, DATA_DIR) print('Done!') diff --git a/research/neural_gpu/wmt_utils.py b/research/neural_gpu/wmt_utils.py index 826fcdf..8c1fa06 100644 --- a/research/neural_gpu/wmt_utils.py +++ b/research/neural_gpu/wmt_utils.py @@ -84,7 +84,26 @@ def get_wmt_enfr_train_set(directory): _WMT_ENFR_TRAIN_URL) print("Extracting tar file %s" % corpus_file) with tarfile.open(corpus_file, "r") as corpus_tar: - corpus_tar.extractall(directory) + def is_within_directory(directory, target): + + abs_directory = os.path.abspath(directory) + abs_target = os.path.abspath(target) + + prefix = os.path.commonprefix([abs_directory, abs_target]) + + return prefix == abs_directory + + def safe_extract(tar, path=".", members=None, *, numeric_owner=False): + + for member in tar.getmembers(): + member_path = os.path.join(path, member.name) + if not is_within_directory(path, member_path): + raise Exception("Attempted Path Traversal in Tar File") + + tar.extractall(path, members, numeric_owner=numeric_owner) + + + safe_extract(corpus_tar, directory) gunzip_file(train_path + ".fr.gz", train_path + ".fr") gunzip_file(train_path + ".en.gz", train_path + ".en") return train_path