Merge pull request #1698 from Trusted-AI/development_issue_1697

Support numpy arrays in logger of clean_label_backdoor_attack

Author: beat-buesser

art/attacks/poisoning/clean_label_backdoor_attack.py

@@ -133,7 +133,7 @@ def poison(  # pylint: disable=W0221
         if any(no_change_detected):  # pragma: no cover
             logger.warning("Perturbed input is the same as original data after PGD. Check params.")
             idx_no_change = np.arange(len(no_change_detected))[no_change_detected]
-            logger.warning("%d indices without change: %d", len(idx_no_change), idx_no_change)
+            logger.warning("%d indices without change: %s", len(idx_no_change), idx_no_change)
 
         # Add backdoor and poison with the same label
         poisoned_input, _ = self.backdoor.poison(perturbed_input, self.target, broadcast=broadcast)