You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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.
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 (Improve attack model types in inference attacks #2253)
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
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
__repr__
to all attacks (Printable representation of Attack objects [JATIC-I2-IBM] #2274)Changed
set_params
to raiseValueError
if a not previously defined attributed is set (AutoAttack skips attacks not supporting targeted mode [JATIC-I2-IBM] #2257)Removed
[None]
Fixed
TargetedUniversalPerturbation
(Update Targeted Universal Perturbation documentation and add example notebook #2212)AdversarialPatchTensorFlowV2
(Fix unsupported operand type(s) for / error in AdversarialPatch in Tensorflow #2276)AutoAttack
to avoid that attacks which do not support targeted mode are skipped (AutoAttack skips attacks not supporting targeted mode [JATIC-I2-IBM] #2257)This discussion was created from the release ART 1.16.0.
Beta Was this translation helpful? Give feedback.
All reactions