Hi @joachim.zaspel, I wanted to thank you for the very informative writeup and detailed code for your issue. Regarding your first question: our team will take a look at your materials and respond here with some further thoughts and analysis.
In the meantime, I’d like to address your second question about the inherent risk of data leaking out. Since this is a separate topic of conversation, I have created a new thread for it here, and added a response: How do you measure the risk of sensitive data leaking out in the synthetic data?