AttributeError: 'attack_data' object has no attribute 'means' about ml_privacy_meter HOT 4 CLOSED

Thank you for providing the additional information. Model A can be used as a shadow model to evaluate the performance of your membership inference model on Model B.
Thank you for the diagram as well, it is a good representation of the data. However, I would like to point out that the non-member set does not have an intersection with the cifar100_train.txt.npy, since this file is only generated using the training data (Member set).

from ml_privacy_meter.

I get that. It's my mistake.

And thank you for your reply (^_^)

from ml_privacy_meter.

Thanks for pointing out this issue. We will test it and fix the issue in the code accordingly.

from ml_privacy_meter.

Hello, more information provided to help you:
The error shot me after this line of code was commented out.

Since I hope your tool can help to calculate the means and standard deviations, instead of assign them like hyperparameters.

And I have a question:
is your program an implementation of supervised training on shadow models?
Namely, is model A a shadow model of model B?

As the code shows me, it's assumed that a subset of the training set is known to the attacker

as well as some data from the same underlying distribution that is not contained in the training set.

Do I get it right? I'm sorry for my lack of expression.

from ml_privacy_meter.