Help Wanted: How To Apply This Tool?

[gongzhimin]

Hello, ml_privacy_meter looks good. it was well encapsulated.
I'm going to apply your tool to evaluate my model.
And I have some questions as follow.

1. I have programmed the model with pytorch, while your tool was based on tensorflow. Can it work in this scenario?
2. In tutorials' MEADME.md, it wrote:
   
   Do the number 26, 6 fit in all models? Should I change them?
3. What's the tool's requirement for dataset? Can I use any dataset to train my model?

[mihirkhandekar]

Hello,
Following are the responses to your queries.

1. The tool expects a Keras/TensorFlow model. You could create the model in Keras and copy layer weights from your PyTorch model, or use some conversion library for the same.
2. The layers/gradient parameter depends on which layer or gradient you want to exploit. The specification of these is given in the documentation - https://github.com/privacytrustlab/ml_privacy_meter#analyzing-a-trained-model
3. Yes, you can use any dataset while following the format given in the datasets documentation - https://github.com/privacytrustlab/ml_privacy_meter/tree/master/datasets

[gongzhimin]

Thanks for your reply!

[gongzhimin]

Oh, sorry to bother you again.
I noticed that you mentioned federated learning.

It is a new field of ML. Why not write a tutorial about how to apply ml_privacy_meter in the FL setting?
I think it will be very popular.