Re:Federated Learning
by ximeng on Saturday May 18, 2019 @01:20AM
(#19945819)
Linked paper on using this for Google Keyboard (https://arxiv.org/pdf/1903.10635.pdf) highlights that there are nevertheless still privacy issues with this approach:
While Federated Learning removes the need to upload raw user material — here OOV words — to the server, the privacy risk of unintended memorization still exists (as demonstrated in (Carlini et al., 2018)). Such risk can be mitigated, usually with some accuracy cost, using techniques including differential privacy (McMahan et al., 2018). Exploring these trade-offs is beyond the scope of this paper.
Re:Federated Learning
by CyanTas on Saturday May 18, 2019 @01:29AM
(#19945837)
You’re not wrong, but it does say those privacy risks can be mitigated with differential privacy. That McMahan et al. paper (which is also Google) makes the accuracy cost seem low.
While Federated Learning removes the need to upload raw user material — here OOV words — to the server, the privacy risk of unintended memorization still exists (as demonstrated in (Carlini et al., 2018)). Such risk can be mitigated, usually with some accuracy cost, using techniques including differential privacy (McMahan et al., 2018). Exploring these trade-offs is beyond the scope of this paper.