mnist result

[Jasper-Bai]

I could not get the adorable DMI attack accuracy and recovery performance on MNIST. I used the same running setting to train the targetor model and launch the DMI attack. could you tell me some possible points causing the bad performance?

[hung-z]

The same comment!

[AlanPeng0897]

In the setting, the MNIST private dataset only contains 5 classes, so the variance of the attack accuracy tends to be large, my suggestion is to use CelebA for evaluation.