A Game-theoretic Framework for Privacy-preserving Federated Learning

arXiv:2304.05836v3 Announce Type: replace-cross
Abstract: 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 …

adversaries aim arxiv attackers cs.ai cs.cr cs.gt cs.lg defenders federated federated learning framework game global presence privacy protection research risk semi