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

User-level privacy #366

Open
ffuuugor opened this issue Mar 11, 2022 · 0 comments
Open

User-level privacy #366

ffuuugor opened this issue Mar 11, 2022 · 0 comments
Labels
enhancement New feature or request

Comments

@ffuuugor
Copy link
Contributor

There's an ongoing research into user-level privacy (e.g. https://openreview.net/pdf?id=74lwg5oxheC, https://proceedings.neurips.cc/paper/2021/file/ec7f346604f518906d35ef0492709f78-Paper.pdf)

There's also a demand for user-lever privacy guarantees for simulating FL tasks: FL is naturally suited for user-level accounting, but this property is not reflected in server-side simulations.

This could be implemented by changing data-loading side only. There are two options:

  • Two step-sampling: first select user, then select event from that user
  • User-level clipping. Instead of implementing per-sample clipping, do per-user clipping
@ffuuugor ffuuugor added the enhancement New feature or request label Mar 11, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

1 participant