Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Tutorial 4 as a client/server scenario #467

Open
boxer-code opened this issue Jan 16, 2024 · 0 comments
Open

Tutorial 4 as a client/server scenario #467

boxer-code opened this issue Jan 16, 2024 · 0 comments
Labels
Type: Question ❔ Question about implementation or some technical aspect

Comments

@boxer-code
Copy link

Question

Is there any good way to transfer the example from tutorial 4 in a client/server scenario? Where the client encrypts the data without having any information about the model and send it to the server to perform the evaluation.

Further Information

Hey everyone! I'm trying to separate the steps from tutorial 4 in two parts. The client part with encryption without any information about the model and the server part without any knowledge about the data. The only condition is that the data was originally in the same format as the data the model is trained with.
Currently, my big problem is that the encryption takes place during the forward method and based on the weights from the model, if I understood it correctly.
Is there any way to encrypt it before and without any knowledges about the weights?

@boxer-code boxer-code added the Type: Question ❔ Question about implementation or some technical aspect label Jan 16, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Type: Question ❔ Question about implementation or some technical aspect
Projects
None yet
Development

No branches or pull requests

1 participant