tapas.threat_models.attacker_knowledge.AttackerKnowledgeOnGenerator

class tapas.threat_models.attacker_knowledge.AttackerKnowledgeOnGenerator

Bases: object

Abstract base class that represents the knowledge that attachers have on the generator used to produce the synthetic datasets. This typically just requires a Generator objct and a choice of length for generated synthetic datasets.

This class supports two modes: training mode, where it behaves like the generator that the attacker knows about, and testing mode, where the real generator is applied. In black-box setting, these are identical, but this allows to model situations where the attacker might have limited information about the generator.

__init__()

Methods

__init__()
generate(training_dataset[, training_mode])	Generate a synthetic dataset from a given training dataset.

Attributes

label

A string to represent this knowledge.

abstract generate(training_dataset: Dataset, training_mode: bool = True)

Generate a synthetic dataset from a given training dataset.

property label

A string to represent this knowledge.