Web: http://arxiv.org/abs/2111.07380

May 4, 2022, 1:12 a.m. | Dario Pasquini, Danilo Francati, Giuseppe Ateniese

cs.LG updates on arXiv.org arxiv.org

Secure aggregation is a cryptographic protocol that securely computes the
aggregation of its inputs. It is pivotal in keeping model updates private in
federated learning. Indeed, the use of secure aggregation prevents the server
from learning the value and the source of the individual model updates provided
by the users, hampering inference and data attribution attacks.

In this work, we show that a malicious server can easily elude secure
aggregation as if the latter were not in place. We devise …

aggregation arxiv federated learning learning model

More from arxiv.org / cs.LG updates on arXiv.org

Director, Applied Mathematics & Computational Research Division

@ Lawrence Berkeley National Lab | Berkeley, Ca

Business Data Analyst

@ MainStreet Family Care | Birmingham, AL

Assistant/Associate Professor of the Practice in Business Analytics

@ Georgetown University McDonough School of Business | Washington DC

Senior Data Science Writer

@ NannyML | Remote

Director of AI/ML Engineering

@ Armis Industries | Remote (US only), St. Louis, California

Digital Analytics Manager

@ Patagonia | Ventura, California