Merge branch 'main' into new_branch

Author: Foxglove144

.github/workflows/ci-pytorch-object-detectors.yml

@@ -50,6 +50,8 @@ jobs:
         run: pytest --cov-report=xml --cov=art --cov-append -q -vv tests/estimators/object_detection/test_pytorch_object_detector.py --framework=pytorch --durations=0
       - name: Run Test Action - test_pytorch_faster_rcnn
         run: pytest --cov-report=xml --cov=art --cov-append -q -vv tests/estimators/object_detection/test_pytorch_faster_rcnn.py --framework=pytorch --durations=0
+      - name: Run Test Action - test_pytorch_detection_transformer
+        run: pytest --cov-report=xml --cov=art --cov-append -q -vv tests/estimators/object_detection/test_pytorch_detection_transformer.py --framework=pytorch --durations=0
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v3
         with:

.github/workflows/dockerhub.yml

@@ -35,7 +35,7 @@ jobs:
         with:
           images: adversarialrobustnesstoolbox/releases
           tags: |
-            type=raw,value={{branch}}-1.14.1-{{sha}}
+            type=raw,value={{branch}}-1.15.0-{{sha}}
             type=semver,pattern={{version}}
 
       - name: Build and push Docker image

README-cn.md

@@ -1,4 +1,4 @@
-# Adversarial Robustness Toolbox (ART) v1.14
+# Adversarial Robustness Toolbox (ART) v1.15
 <p align="center">
   <img src="docs/images/art_lfai.png?raw=true" width="467" title="ART logo">
 </p>

README.md

@@ -1,4 +1,4 @@
-# Adversarial Robustness Toolbox (ART) v1.14
+# Adversarial Robustness Toolbox (ART) v1.15
 <p align="center">
   <img src="docs/images/art_lfai.png?raw=true" width="467" title="ART logo">
 </p>

art/__init__.py

@@ -12,7 +12,7 @@
 from art import preprocessing
 
 # Semantic Version
-__version__ = "1.14.1"
+__version__ = "1.15.0"
 
 # pylint: disable=C0103
 

art/attacks/attack.py

@@ -339,10 +339,10 @@ def __init__(self):
     @abc.abstractmethod
     def poison(
         self,
-        x: np.ndarray,
+        x: Union[np.ndarray, List[np.ndarray]],
         y: List[Dict[str, np.ndarray]],
         **kwargs,
-    ) -> Tuple[np.ndarray, List[Dict[str, np.ndarray]]]:
+    ) -> Tuple[Union[np.ndarray, List[np.ndarray]], List[Dict[str, np.ndarray]]]:
         """
         Generate poisoning examples and return them as an array. This method should be overridden by all concrete
         poisoning attack implementations.

art/attacks/evasion/adversarial_patch/adversarial_patch_pytorch.py

@@ -575,9 +575,9 @@ def __getitem__(self, idx):
                     img = torch.from_numpy(self.x[idx])
 
                     target = {}
-                    target["boxes"] = torch.from_numpy(y[idx]["boxes"])
-                    target["labels"] = torch.from_numpy(y[idx]["labels"])
-                    target["scores"] = torch.from_numpy(y[idx]["scores"])
+                    target["boxes"] = torch.from_numpy(self.y[idx]["boxes"])
+                    target["labels"] = torch.from_numpy(self.y[idx]["labels"])
+                    target["scores"] = torch.from_numpy(self.y[idx]["scores"])
                     mask_i = torch.from_numpy(self.mask[idx])
 
                     return img, target, mask_i
@@ -602,19 +602,33 @@ def __getitem__(self, idx):
                     if isinstance(target, torch.Tensor):
                         target = target.to(self.estimator.device)
                     else:
-                        target["boxes"] = target["boxes"].to(self.estimator.device)
-                        target["labels"] = target["labels"].to(self.estimator.device)
-                        target["scores"] = target["scores"].to(self.estimator.device)
+                        targets = []
+                        for idx in range(target["boxes"].shape[0]):
+                            targets.append(
+                                {
+                                    "boxes": target["boxes"][idx].to(self.estimator.device),
+                                    "labels": target["labels"][idx].to(self.estimator.device),
+                                    "scores": target["scores"][idx].to(self.estimator.device),
+                                }
+                            )
+                        target = targets
                     _ = self._train_step(images=images, target=target, mask=None)
             else:
                 for images, target, mask_i in data_loader:
                     images = images.to(self.estimator.device)
                     if isinstance(target, torch.Tensor):
                         target = target.to(self.estimator.device)
                     else:
-                        target["boxes"] = target["boxes"].to(self.estimator.device)
-                        target["labels"] = target["labels"].to(self.estimator.device)
-                        target["scores"] = target["scores"].to(self.estimator.device)
+                        targets = []
+                        for idx in range(target["boxes"].shape[0]):
+                            targets.append(
+                                {
+                                    "boxes": target["boxes"][idx].to(self.estimator.device),
+                                    "labels": target["labels"][idx].to(self.estimator.device),
+                                    "scores": target["scores"][idx].to(self.estimator.device),
+                                }
+                            )
+                        target = targets
                     mask_i = mask_i.to(self.estimator.device)
                     _ = self._train_step(images=images, target=target, mask=mask_i)
 

art/attacks/evasion/auto_conjugate_gradient.py

@@ -224,7 +224,8 @@ def __call__(self, y_true: tf.Tensor, y_pred: tf.Tensor, *args, **kwargs) -> tf.
                     nb_classes=estimator.nb_classes,
                     input_shape=estimator.input_shape,
                     loss_object=_loss_object_tf,
-                    train_step=estimator._train_step,
+                    optimizer=estimator.optimizer,
+                    train_step=estimator.train_step,
                     channels_first=estimator.channels_first,
                     clip_values=estimator.clip_values,
                     preprocessing_defences=estimator.preprocessing_defences,

art/attacks/evasion/auto_projected_gradient_descent.py

@@ -203,7 +203,8 @@ def __call__(self, y_true: tf.Tensor, y_pred: tf.Tensor, *args, **kwargs) -> tf.
                     nb_classes=estimator.nb_classes,
                     input_shape=estimator.input_shape,
                     loss_object=_loss_object_tf,
-                    train_step=estimator._train_step,
+                    optimizer=estimator.optimizer,
+                    train_step=estimator.train_step,
                     channels_first=estimator.channels_first,
                     clip_values=estimator.clip_values,
                     preprocessing_defences=estimator.preprocessing_defences,

art/attacks/evasion/brendel_bethge.py

@@ -2055,7 +2055,8 @@ def logits_difference(y_true, y_pred):
                 nb_classes=estimator.nb_classes,
                 input_shape=estimator.input_shape,
                 loss_object=self._loss_object,
-                train_step=estimator._train_step,
+                optimizer=estimator.optimizer,
+                train_step=estimator.train_step,
                 channels_first=estimator.channels_first,
                 clip_values=estimator.clip_values,
                 preprocessing_defences=estimator.preprocessing_defences,