Skip to content

ART 1.16.0
Compare
Choose a tag to compare
@beat-buesser beat-buesser released this 22 Sep 14:42
· 572 commits to main since this release
1.16.0
337a15f

This release of ART 1.16.0 introduces multiple estimators for certified robustness and Hugging Face models, adversarial training with Adversarial Weight Perturbation, improvements for inference attacks, and more.

Added

  • Added estimator for smoothed vision transformers as defence against evasion with adversarial patches (#2171)
  • Added estimators for variations of randomised smoothing including MACER, SmoothAdv, and SmoothMix for PyTorch and TensorFlow (#2218)
  • Added adversarial training with Adversarial Weight Perturbation protocol in PyTorch (#2224)
  • Added estimator for Hugging Face models with PyTorch backend (#2245)
  • Added ObjectSeeker certifiably robust defence for object detectors against poisoning and adversarial patches (#2246)
  • Added representation string __repr__ to all attacks (#2274)

Changed

  • Changed inference attacks to support additional attack model types (e.g., KNN, LR, etc.) and replaced scikit-learn's MLPClassifier with a PyTorch neural network model (#2253)
  • Changes attacks's method set_params to raise ValueError if a not previously defined attributed is set (#2257)
  • Changed AutoAttack to support multiprocessing and support running attacks in parallel (#2258)

Removed

[None]

Fixed

  • Fixed docstring of TargetedUniversalPerturbation (#2212)
  • Fixed bug of unsupported operands because of dependency updates in AdversarialPatchTensorFlowV2 (#2276)
  • Fixed bug in AutoAttack to avoid that attacks which do not support targeted mode are skipped (#2257)
Assets 2
Loading
0 Join discussion