联邦学习的博弈理论框架（英文版）

英文标题：A Game-theoretic Framework for Federated Learning中文摘要：提出一种基于博弈论的安全模型，考虑了联邦学习中的隐私泄漏问题和防御者与攻击者的策略问题，通过引入一个神谕作为协调者，优化参与者的收益和隐私泄漏风险。英文摘要：In federated learning, benign participants aim to optimize a global modelcollaboratively. However, the risk of \textit{privacy leakage} cannot beignored in the presence of \textit{semi-honest} adversaries. Existing researchhas focused either on designing protection mechanisms or on inventing attackingmechanisms. While the battle between defenders and attackers