Target

Store information about the target model and data.

class sacroml.attacks.target.Target(model: BaseEstimator | None = None, dataset_name: str = '', features: dict | None = None, X_train: ndarray | None = None, y_train: ndarray | None = None, X_test: ndarray | None = None, y_test: ndarray | None = None, X_orig: ndarray | None = None, y_orig: ndarray | None = None, X_train_orig: ndarray | None = None, y_train_orig: ndarray | None = None, X_test_orig: ndarray | None = None, y_test_orig: ndarray | None = None, proba_train: ndarray | None = None, proba_test: ndarray | None = None)

Store information about the target model and data.

Methods

add_feature(name, indices, encoding)	Add a feature description to the data dictionary.
add_processed_data(X_train, y_train, X_test, ...)	Add a processed and split dataset.
add_raw_data(X_orig, y_orig, X_train_orig, ...)	Add original unprocessed dataset.
add_safemodel_results(data)	Add the results of safemodel disclosure checking.
load([path])	Load the target class from persistent storage.
load_array(arr_path, name)	Load a data array variable from file.
load_model(model_path)	Load the target model.
save([path, ext])	Save the target class to persistent storage.

__init__(model: BaseEstimator | None = None, dataset_name: str = '', features: dict | None = None, X_train: ndarray | None = None, y_train: ndarray | None = None, X_test: ndarray | None = None, y_test: ndarray | None = None, X_orig: ndarray | None = None, y_orig: ndarray | None = None, X_train_orig: ndarray | None = None, y_train_orig: ndarray | None = None, X_test_orig: ndarray | None = None, y_test_orig: ndarray | None = None, proba_train: ndarray | None = None, proba_test: ndarray | None = None) → None

Store information about a target model and associated data.

Parameters:

modelsklearn.base.BaseEstimator | None, optional

Trained target model. Any class that implements the sklearn.base.BaseEstimator interface (i.e. has fit, predict and predict_proba methods)

dataset_namestr

The name of the dataset.

featuresdict

Dictionary describing the dataset features.

X_trainnp.ndarray | None

The (processed) training inputs.

y_trainnp.ndarray | None

The (processed) training outputs.

X_testnp.ndarray | None

The (processed) testing inputs.

y_testnp.ndarray | None

The (processed) testing outputs.

X_orignp.ndarray | None

The original (unprocessed) dataset inputs.

y_orignp.ndarray | None

The original (unprocessed) dataset outputs.

X_train_orignp.ndarray | None

The original (unprocessed) training inputs.

y_train_orignp.ndarray | None

The original (unprocessed) training outputs.

X_test_orignp.ndarray | None

The original (unprocessed) testing inputs.

y_test_orignp.ndarray | None

The original (unprocessed) testing outputs.

proba_trainnp.ndarray | None

The model predicted training probabilities.

proba_testnp.ndarray | None

The model predicted testing probabilities.

add_feature(name: str, indices: list[int], encoding: str) → None

Add a feature description to the data dictionary.

add_processed_data(X_train: ndarray, y_train: ndarray, X_test: ndarray, y_test: ndarray) → None

Add a processed and split dataset.

add_raw_data(X_orig: ndarray, y_orig: ndarray, X_train_orig: ndarray, y_train_orig: ndarray, X_test_orig: ndarray, y_test_orig: ndarray) → None

Add original unprocessed dataset.

add_safemodel_results(data: list) → None

Add the results of safemodel disclosure checking.

Parameters:

datalist

The results of safemodel disclosure checking.

load(path: str = 'target') → None

Load the target class from persistent storage.

Parameters:

pathstr

Name of the output folder containing a target yaml file.

load_array(arr_path: str, name: str) → None

Load a data array variable from file.

Parameters:

arr_pathstr

Filename of a data array.

namestr

Name of the data array to load.

load_model(model_path: str) → None

Load the target model.

Parameters:

model_pathstr

Path to load the model.

save(path: str = 'target', ext: str = 'pkl') → None

Save the target class to persistent storage.

Parameters:

pathstr

Name of the output folder to save target information.

extstr

File extension defining the model saved format, e.g., “pkl” or “sav”.