# A Game-theoretic Framework for Privacy-preserving Federated Learning

arXiv: https://arxiv.org/abs/2304.05836 · HTML: https://mlsanity.com/paper/2304.05836/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 56 references that are in the map.
- First posted on arXiv 11 Apr 2023.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Federated Optimization: Distributed Machine Learning for On-Device Intelligence](https://mlsanity.com/paper/1610.02527/) (2016)
- [Differentially Private Federated Learning: A Client Level Perspective](https://mlsanity.com/paper/1712.07557/) (2017)
- [iDLG: Improved Deep Leakage from Gradients](https://mlsanity.com/paper/2001.02610/) (2020)
- [Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning](https://mlsanity.com/paper/1702.07464/) (2017)
- [SplitFed: When Federated Learning Meets Split Learning](https://mlsanity.com/paper/2004.12088/) (2020)
- [Distributed learning of deep neural network over multiple agents](https://mlsanity.com/paper/1810.06060/) (2018)
- [Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning](https://mlsanity.com/paper/1812.00535/) (2018)
- [LDP-Fed: Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2006.03637/) (2020)
- [Model-sharing Games: Analyzing Federated Learning Under Voluntary Participation](https://mlsanity.com/paper/2010.00753/) (2020)
- [Incentive Mechanisms for Federated Learning: From Economic and Game Theoretic Perspective](https://mlsanity.com/paper/2111.11850/) (2021)
- [No Free Lunch Theorem for Security and Utility in Federated Learning](https://mlsanity.com/paper/2203.05816/) (2022)
- [Trading Off Privacy, Utility and Efficiency in Federated Learning](https://mlsanity.com/paper/2209.00230/) (2022)
- [From Robustness to Privacy and Back](https://mlsanity.com/paper/2302.01855/) (2023)
- [Federated Deep Learning with Bayesian Privacy](https://mlsanity.com/paper/2109.13012/) (2021)
- [Nash Equilibria in the Response Strategy of Correlated Games](https://mlsanity.com/paper/1809.03860/) (2018)

## Built on by (most cited first, 2 of 2)

- [Ten Challenging Problems in Federated Foundation Models](https://mlsanity.com/paper/2502.12176/) (2025)
- [Nonlinear Equilibrium Transitions in a Potential Game Model for Federated Learning](https://mlsanity.com/paper/2411.11793/) (2024)

## Abstract (arXiv)

In federated learning, benign participants aim to optimize a global model collaboratively. However, the risk of textitprivacy leakage cannot be ignored in the presence of textitsemi-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 textitincomplete information inherent in this situation, we propose associating the FLPG with an textitoracle 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 textitnot to attack.