Skip to content

ART 1.17.0
Compare
Choose a tag to compare
@beat-buesser beat-buesser released this 27 Dec 22:17
· 205 commits to main since this release
1.17.0
044f87e

This release of ART 1.17.0 introduces new adversarial training protocols, membership inference attacks, composite adversarial attacks for evasion and more.

Added

  • Added Composite Adversarial Attack as evasion attack in PyTorch (#2287)
  • Added support for black-box membership inference attacks without true labels (#2293)
  • Added verbose option for progress bars in methods fit and predict of all classification estimators (#2334)
  • Added Oracle Aligned Adversarial Training (OAAT) in PyTorch (#2348)

Changed

[None]

Removed

[None]

Fixed

  • Fixed bug in ActivateDefense and SpectralSignatures poisoning defences by flattening the outputs when calling get_activations() (#2327)
  • Fixed bug in Hugging Face classification estimator to correctly infer device if provided model is already on GPU (#2300)
Assets 2
0 Join discussion