attack_data.py

# `saved_path` is required for obtaining the training data that was used to
# train the target classification model, in "npy" format
saved_path = "datasets/purchase100.txt.npy"

# Similar to `saved_path` being used to form the memberset for attack model, 
# `dataset_path` is used for forming the non-member set of the training data of
# attack model.
dataset_path = 'datasets/purchase100.txt'

datahandlerA = ml_privacy_meter.utils.attack_data.attack_data(dataset_path=dataset_path,
							     member_dataset_path=saved_path,
							     batch_size=64,
							     attack_percentage=50)