A Game-theoretic Framework for Privacy-preserving Federated Learning
Authors:
- Xiaojin ZhangXZXiaojin Zhang
- Lixin FanLFLixin Fan
- Siwei WangSWSiwei Wang
- Wenjie LiWLWenjie Li
- Kai ChenKCKai Chen
- Qiang YangQYQiang Yang
Preprint
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 that considers both FL defenders and attackers in terms of their respective payoffs, which include computational costs, FL model utilities, and privacy leakage risks. We name this game the federated learning privacy game (FLPG), in which neither defenders nor attackers are aware of all participants' payoffs. To handle the \textit{incomplete information} inherent in this situation, we propose associating the FLPG with an \textit{oracle} that has two primary responsibilities. First, the oracle provides lower and upper bounds of the payoffs for the players. Second, the oracle acts as a correlation device, privately providing suggested actions to each player. With this novel framework, we analyze the optimal strategies of defenders and attackers. Furthermore, we derive and demonstrate conditions under which the attacker, as a rational decision-maker, should always follow the oracle's suggestion \textit{not to attack}.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Trading Off Privacy, Utility, and Efficiency in Federated LearningACM Transactions on Intelligent Systems and Technology, 2023
- No Free Lunch Theorem for Security and Utility in Federated LearningACM Transactions on Intelligent Systems and Technology, 2022
- A Privacy-Preserving Game Model for Local Differential Privacy by Using Information-Theoretic ApproachIEEE Access, 2020
- Deep Leakage from Gradients2020
- A Learning-Based Incentive Mechanism for Federated LearningIEEE Internet of Things Journal, 2020
- Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning2019
- Distributed learning of deep neural network over multiple agentsJournal of Network and Computer Applications, 2018
- Game Theory Based Correlated Privacy Preserving Analysis in Big DataIEEE Transactions on Big Data, 2017
- Robust game theoryMathematical Programming, 2006
- The Common Prior Assumption in Economic TheoryEconomics and Philosophy, 1995