Fixed TypeError in example and annotation.

examples/model_security/model_attacks/black_box/mnist_attack_nes.py

@@ -140,7 +140,7 @@ def test_nes_mnist_attack():
         target_image = create_target_images(test_images, true_labels,
                                             target_class)
         nes_instance.set_target_images(target_image)
-        tag, adv, queries = nes_instance.generate(initial_img, target_class)
+        tag, adv, queries = nes_instance.generate(np.array(initial_img), np.array(target_class))
         if tag[0]:
             success += 1
         queries_num += queries[0]

examples/model_security/model_attacks/black_box/mnist_attack_salt_and_pepper.py

@@ -108,6 +108,7 @@ def test_salt_and_pepper_attack_on_mnist():
         # rescale predict confidences into (0, 1).
         pred_logits_adv = softmax(pred_logits_adv, axis=1)
         adv_preds.extend(pred_logits_adv)
+    adv_preds = np.array(adv_preds)
     accuracy_adv = np.mean(np.equal(np.max(adv_preds, axis=1), true_labels))
     LOGGER.info(TAG, "prediction accuracy after attacking is : %g",
                 accuracy_adv)

mindarmour/adv_robustness/attacks/deep_fool.py

@@ -63,14 +63,14 @@ def _deepfool_detection_scores(inputs, gt_boxes, gt_labels, network):
     pred_labels = np.argmax(pred_logits, axis=2)
     det_scores = []
     correct_labels_num = []
-    gt_boxes_num = gt_boxes.shape[0]
+    gt_boxes_num = gt_boxes.shape[1]
     iou_thres = 0.5
     for idx, (boxes, labels) in enumerate(zip(box_and_confi, pred_labels)):
         score = 0
         box_num = boxes.shape[0]
-        correct_label_flag = np.zeros(gt_labels.shape)
         gt_boxes_idx = gt_boxes[idx]
         gt_labels_idx = gt_labels[idx]
+        correct_label_flag = np.zeros(gt_labels_idx.shape)
         for i in range(box_num):
             pred_box = boxes[i]
             max_iou_confi = 0
@@ -102,6 +102,10 @@ class DeepFool(Attack):
         network (Cell): Target model.
         num_classes (int): Number of labels of model output, which should be
             greater than zero.
+        model_type (str): Tye type of targeted model. 'classification' and 'detection' are supported now.
+            default: 'classification'.
+        reserve_ratio (Union[int, float]): The percentage of objects that can be detected after attaks,
+            specifically for model_type='detection'. Reserve_ratio should be in the range of (0, 1). Default: 0.3.
         max_iters (int): Max iterations, which should be
             greater than zero. Default: 50.
         overshoot (float): Overshoot parameter. Default: 0.02.

mindarmour/utils/_check_param.py

@@ -138,7 +138,7 @@ def check_numpy_param(arg_name, arg_value):
 
     Args:
         arg_name (str): Name of parameter.
-        arg_value (Union[list, tuple, numpy.ndarray]): Value for check.
+        arg_value (numpy.ndarray): Value for check.
 
     Returns:
         numpy.ndarray, if `value` is not empty, return `value` with type of
@@ -146,7 +146,7 @@ def check_numpy_param(arg_name, arg_value):
 
     Raises:
         ValueError: If value is empty.
-        ValueError: If value type is not in (list, tuple, numpy.ndarray).
+        ValueError: If value type is not numpy.ndarray.
     """
     _ = _check_array_not_empty(arg_name, arg_value)
     if isinstance(arg_value, np.ndarray):
@@ -165,15 +165,15 @@ def check_pair_numpy_param(inputs_name, inputs, labels_name, labels):
 
     Args:
         inputs_name (str): Name of inputs.
-        inputs (Union[list, tuple, numpy.ndarray]): Inputs.
+        inputs (numpy.ndarray): Inputs.
         labels_name (str): Name of labels.
-        labels (Union[list, tuple, numpy.ndarray]): Labels of `inputs`.
+        labels (numpy.ndarray): Labels of `inputs`.
 
     Returns:
-        - Union[list, tuple, numpy.ndarray], if `inputs` 's dimension equals to
+        - numpy.ndarray, if `inputs` 's dimension equals to
           `labels`, return inputs with type of numpy.ndarray.
 
-        - Union[list, tuple, numpy.ndarray], if `inputs` 's dimension equals to
+        - numpy.ndarray, if `inputs` 's dimension equals to
           `labels` , return labels with type of numpy.ndarray.
 
     Raises:

tests/ut/python/adv_robustness/attacks/test_deep_fool.py

@@ -66,9 +66,9 @@ class Net2(Cell):
         self._softmax = P.Softmax()
 
     def construct(self, inputs1, inputs2):
-        out1 = self._softmax(inputs2)
-        out2 = self._softmax(inputs1)
-        return out1, out2
+        out1 = self._softmax(inputs1)
+        out2 = self._softmax(inputs2)
+        return out2, out1
 
 
 @pytest.mark.level0
@@ -108,13 +108,15 @@ def test_deepfool_attack_detection():
     net = Net2()
     inputs1_np = np.random.random((2, 10, 10)).astype(np.float32)
     inputs2_np = np.random.random((2, 10, 5)).astype(np.float32)
-    gt_boxes = inputs1_np[:, :, 0: 5]
-    gt_labels = np.argmax(inputs1_np, axis=2)
+    gt_boxes, gt_logits = net(Tensor(inputs1_np), Tensor(inputs2_np))
+    gt_boxes, gt_logits = gt_boxes.asnumpy(), gt_logits.asnumpy()
+    gt_labels = np.argmax(gt_logits, axis=2)
     num_classes = 10
 
     attack = DeepFool(net, num_classes, model_type='detection', reserve_ratio=0.3,
                       bounds=(0.0, 1.0))
-    _ = attack.generate((inputs1_np, inputs2_np), (gt_boxes, gt_labels))
+    adv_data = attack.generate((inputs1_np, inputs2_np), (gt_boxes, gt_labels))
+    assert np.any(adv_data != inputs1_np)
 
 
 @pytest.mark.level0