github Trusted-AI/adversarial-robustness-toolbox 1.11.0
ART 1.11.0

latest releases: 1.20.1, 1.20.0, 1.19.2...
3 years ago

This release of ART 1.11.0 introduces estimators for YOLO object detection and regression models, the first audio poisoning attack, new query-efficient black-box evasion attacks, certified defenses against adversarial patch attacks, metrics quantifying membership inference and more.

Added

  • Added Momentum-Iterative FGSM evasion attack in MomentumIterativeMethod and added optional momentum to loss gradients in ProjectedGradientDescent* attacks. (#1614)
  • Added metrics measuring worst-case scores of membership inference attacks. (#1709)
  • Added estimator for YOLO v3 models in PyTorch in PyTorchYolo. (#1715)
  • Added estimators for de-randomized smoothing certification against patch attacks in PyTorchDeRandomizedSmoothing and TensorFlowV2DeRandomizedSmoothing. (#1729)
  • Added query-efficient hard-label black-box evasion attack Sign-Opt in SignOPTAttack. (#1730)
  • Added Sleeper Agent poisoning attack PyTorch in SleeperAgentAttack. (#1736)
  • Added exclusionary reclassification to ActivationDefence. (#1738)
  • Added dirty-label backdoor poisoning attack on audio classification in art.attacks.poisoning.perturbations.audio_perturbations. (#1740)
  • Added estimators for regression in PyTorchRegressor and KerasRegressor for PyTorch and Keras. (#1651)
  • Added option for targeted attacks to AdversarialPatch and AdversarialPatchNumpy. (#1759)

Changed

  • Changed check_and_transform_label_format for nb_classes=None to automatically determine the number of classes in the provided labels. (#1747)
  • Added additional documentation to ZOOAttack and cleaned up the code of method compare. (#1648)
  • Changed default value for number of epochs nb_epochs in AdversarialTrainerMadryPGD to match 80'000 training steps of Madry et al. (#1758)

Removed

[None]

Fixed

  • Fixed PyTorchClassifier.clone_fore_refitting by deleting optimizer from parameters before calling set_param() to avoid creating the cloned model with the old optimizer. (#1742)
  • Fixed missing propagation of nb_classes to method check_and_transform_label_format in inference attacks. (#1713)

Don't miss a new adversarial-robustness-toolbox release

NewReleases is sending notifications on new releases.