A Game-theoretic Framework for Federated Learning. (arXiv:2304.05836v1 [cs.LG])

In federated learning, benign participants aim to optimize a global model
collaboratively. However, the risk of \textit{privacy leakage} cannot be
ignored in the presence of \textit{semi-honest} adversaries. Existing research
has focused either on designing protection mechanisms or on inventing attacking
mechanisms. While the battle between defenders and attackers seems
never-ending, we are concerned with one critical question: is it possible to
prevent potential attacks in advance? To address this, we propose the first
game-theoretic framework that considers both FL defenders …

address adversaries aim attackers attacks computational critical defenders federated learning framework game global privacy protection question research risk terms