May 26, 2023, 1:19 a.m. | Xinchi Qiu, Ilias Leontiadis, Luca Melis, Alex Sablayrolles, Pierre Stock

cs.CR updates on

Privacy-Preserving machine learning (PPML) can help us train and deploy
models that utilize private information. In particular, on-device Machine
Learning allows us to completely avoid sharing information with a third-party
server during inference. However, on-device models are typically less accurate
when compared to the server counterparts due to the fact that (1) they
typically only rely on a small set of on-device features and (2) they need to
be small enough to run efficiently on end-user devices. Split Learning (SL) …

attack device fact information machine machine learning party privacy private server sharing split learning third third-party train

More from / cs.CR updates on

Consultant infrastructure sécurité H/F

@ Hifield | Sèvres, France

IT Security Analyst

@ Current | Greenville, SC, United States

Information Security Specialist (Hybrid)

@ Netcompany-Intrasoft | Valetta, Malta

Consultant Cybersécurité Industrielle (H/F)

@ ADVENS | Paris, France

Africa Talent by Deloitte – IRL Application Security, Cyber cloud Assistant Manager

@ Deloitte | Midrand, South Africa

Africa Talent by Deloitte – IRL Application Security, Infrastructure Security Senior Consultant

@ Deloitte | Midrand, South Africa