update docs

RELEASE.md

@@ -1,3 +1,23 @@
+# MindArmour 1.3.0-rc1
+
+## MindArmour 1.3.0 Release Notes
+
+### Major Features and Improvements
+
+#### Privacy
+
+* [STABLE] Data Drift Detection for Time Series Data
+
+### Bug fixes
+
+* [BUGFIX] Optimization of API description.
+
+### Contributors
+
+Thanks goes to these wonderful people:
+
+Wu Xiaoyu，Liu Zhidan, Jin Xiulang, Liu Luobin, Liu Liu
+
 # MindArmour 1.2.0
 
 ## MindArmour 1.2.0 Release Notes

mindarmour/adv_robustness/attacks/black/pointwise_attack.py

@@ -39,7 +39,7 @@ class PointWiseAttack(Attack):
 
     Args:
         model (BlackModel): Target model.
-        max_iter (int): Max rounds of iteration to generate adversarial image. Default: 100.
+        max_iter (int): Max rounds of iteration to generate adversarial image. Default: 1000.
         search_iter (int): Max rounds of binary search. Default: 10.
         is_targeted (bool): If True, targeted attack. If False, untargeted attack. Default: False.
         init_attack (Attack): Attack used to find a starting point. Default: None.