2

We are trying to give a model to collaborators but would like to protect the IP. What are some ways to encrypt/hide/compile the definition when sharing a trained model?

illan
  • 21
  • 1

1 Answers1

0

One way to protect the IP of a trained model is to put the model behind an API. Give only limited API end-point access.

Brian Spiering
  • 20,142
  • 2
  • 25
  • 102
  • Yes, something like docker. I did think of that one. Is there no way to "compile" a model to something like a binary? – illan Feb 08 '23 at 22:18