secmlt.adv.poisoning package

Submodules

secmlt.adv.poisoning.backdoor module

Simple backdoor attack in PyTorch.

class secmlt.adv.poisoning.backdoor.BackdoorDatasetPyTorch(dataset: Dataset, data_manipulation_func: callable, trigger_label: int = 0, portion: float | None = None, poisoned_indexes: list[int] | torch.Tensor = None)

Bases: PoisoningDatasetPyTorch

Dataset class for adding triggers for backdoor attacks.

secmlt.adv.poisoning.base_data_poisoning module

Base class for data poisoning.

class secmlt.adv.poisoning.base_data_poisoning.PoisoningDatasetPyTorch(dataset: ~torch.utils.data.dataset.Dataset, data_manipulation_func: callable = <function PoisoningDatasetPyTorch.<lambda>>, label_manipulation_func: callable = <function PoisoningDatasetPyTorch.<lambda>>, portion: float | None = None, poisoned_indexes: list[int] | ~torch.Tensor | None = None)

Bases: Dataset

Dataset class for adding poisoning samples.

Module contents

Backdoor attacks.