On the Conflict of Robustness and Learning in Collaborative Machine Learning

arXiv:2402.13700v1 Announce Type: cross
Abstract: Collaborative Machine Learning (CML) allows participants to jointly train a machine learning model while keeping their training data private. In scenarios where privacy is a strong requirement, such as health-related applications, safety is also a primary concern. This means that privacy-preserving CML processes must produce models that output correct and reliable decisions \emph{even in the presence of potentially untrusted participants}. In response to this issue, researchers propose to use \textit{robust aggregators} that rely on metrics …

applications arxiv conflict cs.cr cs.lg data health machine machine learning privacy private processes robustness safety train training training data