[meetings] Agenda Request - Learning and inference inside a trusted server (#187)

fhoering has just created a new issue for https://github.com/patcg/meetings:

== Agenda Request - Learning and inference inside a trusted server ==
## Agenda+: What do you want to discuss?

As a follow up of the presentation on Private Conversion Measurement via Global and Local DP (https://github.com/patcg/meetings/files/14936682/PATCG_Boston_private_learning.pdf) Criteo would like to present our working assumptions for learning and inference inside a trusted server.

We will cover TEE based trusted servers and compare with MPC based approaches like the Hybrid Proposal/Firefox's Private Measurement API.

Covered topics
- assumed trust model
- experimental workflow
- constraints around differential privacy
- engineering constraints

## Time

60 minutes

### Links

Links to come


Please view or discuss this issue at https://github.com/patcg/meetings/issues/187 using your GitHub account


-- 
Sent via github-notify-ml as configured in https://github.com/w3c/github-notify-ml-config

Received on Wednesday, 17 July 2024 09:22:51 UTC