all InfoSec news
Is Federated Learning a Practical PET Yet?. (arXiv:2301.04017v1 [cs.CR])
cs.CR updates on arXiv.org arxiv.org
Federated learning (FL) is a framework for users to jointly train a machine
learning model. FL is promoted as a privacy-enhancing technology (PET) that
provides data minimization: data never "leaves" personal devices and users
share only model updates with a server (e.g., a company) coordinating the
distributed training. We assess the realistic (i.e., worst-case) privacy
guarantees that are provided to users who are unable to trust the server. To
this end, we propose an attack against FL protected with distributed …
case data devices distributed end federated learning framework machine machine learning minimization personal personal devices privacy server share technology train training trust updates