To prevent implicit privacy disclosure in sharing gradients among data owners (DOs) under federated learning (FL), differential privacy (DP) and its variants have become a common practice to offer formal privacy guarantees with low overheads. However, individual DOs generally tend to inject larger DP noises for stronger privacy provisions (which entails severe degradation of model utility), while the curator (i.e., aggregation server) aims to minimize the overall effect of added random noises for satisfactory model performance. To address this conflicting goal, we propose a novel dynamic privacy pricing (DyPP) game which allows DOs to sell individual privacy (by lowering the scale of locally added DP noise) for differentiated economic compensations (offered by the curator), thereby enhancing FL model utility. Considering multi-dimensional information asymmetry among players (e.g., DO's data distribution and privacy preference, and curator's maximum affordable payment) as well as their varying private information in distinct FL tasks, it is hard to directly attain the Nash equilibrium of the mixed-strategy DyPP game. Alternatively, we devise a fast reinforcement learning algorithm with two layers to quickly learn the optimal mixed noise-saving strategy of DOs and the optimal mixed pricing strategy of the curator without prior knowledge of players' private information. Experiments on real datasets validate the feasibility and effectiveness of the proposed scheme in terms of faster convergence speed and enhanced FL model utility with lower payment costs.
Optimal Auctions vs. Anonymous Pricing: Beyond Linear Utility
对于具有线性效用的代理人来说，向具有独立但不相同分布的价值的代理人出售单一物品的收入最优机制是复杂的（Myerson，1981），并且对于具有非线性效用的代理人来说没有封闭形式的表征（参见1981）。Alaei等人，2012年）。尽管如此，对于满足自然规律性的线性效用代理，Alaei et al.（2018）表明，简单地发布匿名价格是一种e近似。我们给出了一个参数化的正则性属性，扩展到代理商的非线性效用，并表明，近似界的匿名定价定期代理商近似扩展到代理商，满足这个近似的正则性属性。我们应用这个近似框架来证明匿名定价是一个常数近似的收入最优的单项目拍卖代理公共预算的效用，私人预算的效用，和（一个特殊情况下）风险厌恶的效用。
DaringFed: A Dynamic Bayesian Persuasion Pricing for Online Federated Learning under Two-sided Incomplete Information
School of Computer Science and Technology, Wuhan University of Science and Technology（武汉科技大学计算机科学与技术学院）；Key Laboratory of Social Computing and Cognitive Intelligence (Dalian University of Technology), Ministry of Education, China（大连理工大学社会计算与认知智能重点实验室（教育部））；Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System, Wuhan University of Science and Technology, China（湖北省智能信息处理与实时工业系统重点实验室（武汉科技大学））；College of Computer Science, Inner Mongolia University, China（内蒙古大学计算机学院）；School of Computer Science and Technology, Huazhong University of Science and Technology, China（华中科技大学计算机科学与技术学院）；School of Automation, Southeast University, China（东南大学自动化学院）
From Stream to Pool: Pricing Under the Law of Diminishing Marginal Utility
Joseph M. Katz Graduate School of Business, University of Pittsburgh（匹兹堡大学约瑟夫·M·卡茨商学院）；Center of Data Science for Enterprise and Society (CDSES), Cornell University（康奈尔大学企业与社会数据科学中心）；Naveen Jindal School of Management, UT Dallas（德克萨斯大学达拉斯分校纳文·金达尔管理学院）
Price-Discrimination Game for Distributed Resource Management in Federated Learning
School of Computer Science and Technology, China University of Mining and Technology（中国矿业大学计算机科学与技术学院）；Department of Electronic and Electrical Engineering, University College London（伦敦大学学院电子与电气工程系）
Secure and Privacy-Preserving Federated Learning via Co-Utility
UNESCO Chair in Data Privacy（联合国教科文组织数据隐私教席）；CYBERCAT-Center for Cybersecurity Research of Catalonia（CYBERCAT-加泰罗尼亚网络安全研究中心）；Universitat Rovira i Virgili（罗维拉-威尔吉利大学）
Stochastic Online Fisher Markets: Static Pricing Limits and Adaptive Enhancements
Institute for Computational and Mathematical Engineering, Stanford University（斯坦福大学计算与数学工程研究所）；Department of Management Science and Engineering, Stanford University（斯坦福大学管理科学与工程学院）
