secmlt.adv package

Subpackages

• secmlt.adv.evasion package
  • Subpackages
    • secmlt.adv.evasion.advlib_attacks package
      • Submodules
      • secmlt.adv.evasion.advlib_attacks.advlib_base module
      • secmlt.adv.evasion.advlib_attacks.advlib_pgd module
      • Module contents
    • secmlt.adv.evasion.aggregators package
      • Submodules
      • secmlt.adv.evasion.aggregators.ensemble module
      • Module contents
    • secmlt.adv.evasion.foolbox_attacks package
      • Submodules
      • secmlt.adv.evasion.foolbox_attacks.foolbox_base module
      • secmlt.adv.evasion.foolbox_attacks.foolbox_pgd module
      • Module contents
  • Submodules
  • secmlt.adv.evasion.base_evasion_attack module
    • BaseEvasionAttack
      • BaseEvasionAttack.__call__()
      • BaseEvasionAttack.check_perturbation_model_available()
      • BaseEvasionAttack.get_perturbation_models()
      • BaseEvasionAttack.trackers
    • BaseEvasionAttackCreator
      • BaseEvasionAttackCreator.check_backend_available()
      • BaseEvasionAttackCreator.get_advlib_implementation()
      • BaseEvasionAttackCreator.get_backends()
      • BaseEvasionAttackCreator.get_foolbox_implementation()
      • BaseEvasionAttackCreator.get_implementation()
  • secmlt.adv.evasion.modular_attack module
    • ModularEvasionAttackFixedEps
      • ModularEvasionAttackFixedEps.__init__()
      • ModularEvasionAttackFixedEps.forward_loss()
      • ModularEvasionAttackFixedEps.get_perturbation_models()
      • ModularEvasionAttackFixedEps.manipulation_function
  • secmlt.adv.evasion.perturbation_models module
    • LpPerturbationModels
      • LpPerturbationModels.L0
      • LpPerturbationModels.L1
      • LpPerturbationModels.L2
      • LpPerturbationModels.LINF
      • LpPerturbationModels.get_p()
      • LpPerturbationModels.is_perturbation_model_available()
      • LpPerturbationModels.pert_models
  • secmlt.adv.evasion.pgd module
    • PGD
      • PGD.__new__()
      • PGD.get_backends()
    • PGDNative
      • PGDNative.__init__()
  • Module contents
• secmlt.adv.poisoning package
  • Submodules
  • secmlt.adv.poisoning.backdoor module
    • BackdoorDatasetPyTorch
      • BackdoorDatasetPyTorch.__init__()
  • secmlt.adv.poisoning.base_data_poisoning module
    • PoisoningDatasetPyTorch
      • PoisoningDatasetPyTorch.__getitem__()
      • PoisoningDatasetPyTorch.__init__()
      • PoisoningDatasetPyTorch.__len__()
  • Module contents

Submodules

secmlt.adv.backends module

Available backends for running adversarial attacks.

class secmlt.adv.backends.Backends

Bases: object

Available backends.

ADVLIB = 'advlib'

FOOLBOX = 'foolbox'

NATIVE = 'native'

Module contents

Adversarial functionalities.