our contribution well: " DLG is the first to shows a malicious player can recover private training data in collaborative

We thank all reviewers for their comments. All reviewers think it is an interesting paper. Both R1 and R3 are positive overall in their comments (R1 "easy to read and well structured", For all typos/grammar mistakes, we have revised our writing accordingly. R2: DLG may not work for accumulated gradients / Contrived settings. Our work aims to raise people's awareness We also add a comparison on property inference task in Tab.