In this paper, we first give an introduction to the theoretical basis of the privacy-utility equilibrium in federated learning based on Bayesian privacy definitions and total variation distance privacy definitions. We then present the \textit{Learn-to-Distort-Data} framework, which provides a principled approach to navigate the privacy-utility equilibrium by explicitly modeling the distortion introduced by the privacy-preserving mechanism as a learnable variable and optimizing it jointly with the model parameters. We demonstrate the applicability of our framework to a variety of privacy-preserving mechanisms on the basis of data distortion and highlight its connections to related areas such as adversarial training, input robustness, and unlearnable examples. These connections enable leveraging techniques from these areas to design effective algorithms for privacy-utility equilibrium in federated learning under the \textit{Learn-to-Distort-Data} framework.

翻译：本文首先基于贝叶斯隐私定义和全变差距离隐私定义，介绍了联邦学习中隐私-效用均衡的理论基础。随后，我们提出了\textit{学习扭曲数据}框架，该框架通过将隐私保护机制引入的数据失真显式建模为可学习变量，并使其与模型参数联合优化，为探索隐私-效用均衡提供了一种原则性方法。我们展示了该框架可适用于多种基于数据失真的隐私保护机制，并阐明了其与对抗训练、输入鲁棒性及不可学习示例等相关领域的联系。这些联系使得能够利用相关领域的技术，在\textit{学习扭曲数据}框架下为联邦学习的隐私-效用均衡设计有效算法。