ART 1.18.0

[beat-buesser]

This release of ART 1.18.0 introduces Overload Attack on object detection models and provides fast accurate loss gradients in Projected Gradient Descent for all norms.

Added

• Added Overload Attack on object detection models (Added support for Overload attack #2337)
• Added support for all norms in Projected Gradient Descent attacks ([FIX + Enhancement] FGM and PGD: fix L1 and extend to Lp #2382)
• Added support for feature scaling in inference attacks (Support scaling input features to attacks  #2384)

Changed

• Replaced model specific estimators for Yolo and Faster-RCNN with single estimator for all object detection models in PyTorch (Subclass PyTorchYolo and PyTorchDetectionTransformer off PyTorchObjectDetector #2321 )

Removed

[None]

Fixed

• Fixed scaling of gradients of non-L[2, infinity] norms in Projected Gradient Descent attacks ([FIX + Enhancement] FGM and PGD: fix L1 and extend to Lp #2382)

---

This discussion was created from the release ARt 1.18.0.