Differential Privacy in Federated Learning: An Evolutionary Game Analysis
Source abstract
Abstract
This paper examines federated learning, a decentralized machine learning paradigm, focusing on privacy challenges. We introduce differential privacy mechanisms to protect privacy and quantify their impact on global model performance. Using evolutionary game theory, we establish a framework to analyze strategy dynamics and define utilities for different strategies based on Gaussian noise powers and training iterations. A differential privacy federated learning model (DPFLM) is analyzed within this framework. A key contribution is the thorough existence and stability analysis, identifying evolutionarily stable strategies (ESSs) and confirming their stability through simulations. This research provides theoretical insights for enhancing privacy protection in federated learning systems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Privacy-Preserving Technologies in Data · Privacy, Security, and Data Protection · Mobile Crowdsensing and Crowdsourcing
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China
School of Information and Electronic Engineering, Zhejiang Gongshang University, Hangzhou 310018, China
Funding
Zhejiang Provincial Natural Science Foundation of China
References (38)
Show source-provided references
1. Trustworthy AI: From principles to practices
2. Secure, privacy-preserving and federated machine learning in medical imaging10.1038/s42256-020-0186-1 ↗
3. When machine learning meets privacy: A survey and outlook
4. Security and privacy on generative data in aigc: A survey
5. Shokri, R., Stronati, M., Song, C., and Shmatikov, V. (2017, January 22–24). Membership inference attacks against machine learning models. Proceedings of the 2017 IEEE Symposium on Security and Privacy (SP), San Jose, CA, USA.10.1109/SP.2017.41 ↗
6. Federated learning: Challenges, methods, and future directions
7. Federated learning with differential privacy: Algorithms and performance analysis10.1109/TIFS.2020.2988575 ↗
8. Personalized federated learning with differential privacy10.1109/JIOT.2020.2991416 ↗
9. Geyer, R.C., Klein, T., and Nabi, M. (2017). Differentially private federated learning: A client level perspective. arXiv.
10. Owen, G. (2013). Game Theory, Emerald Group Publishing.10.1016/B978-0-12-373932-2.00178-2 ↗
11. Evolutionary game dynamics10.1090/S0273-0979-03-00988-1 ↗
12. Sandholm, W.H. (2020). Evolutionary game theory. Complex Social and Behavioral Systems: Game Theory and Agent-Based Models, Springer.10.1007/978-1-0716-0368-0_188 ↗
13. Evolutionary games on graphs10.1016/j.physrep.2007.04.004 ↗
14. Zheng, C., Wang, L., Xu, Z., and Li, H. (2024, January 22–24). Optimizing Privacy in Federated Learning with MPC and Differential Privacy. Proceedings of the 2024 3rd Asia Conference on Algorithms, Computing and Machine Learning, Shanghai, China.10.1145/3654823.3654854 ↗
15. Khan, A., Thij, M.t., Thuijsman, F., and Wilbik, A. (2023). Incentive Allocation in Vertical Federated Learning Based on Bankruptcy Problem. arXiv.10.1109/FLTA63145.2024.10839765 ↗
16. Talajić, M., Vrankić, I., and Pejić Bach, M. (2024). Strategic Management of Workforce Diversity: An Evolutionary Game Theory Approach as a Foundation for AI-Driven Systems. Information, 15.10.3390/info15060366 ↗
17. Optimized shared energy storage in a peer-to-peer energy trading market: Two-stage strategic model regards bargaining and evolutionary game theory10.1016/j.renene.2024.120190 ↗
18. A novel incentive mechanism for federated learning over wireless communications10.1109/TAI.2024.3419757 ↗
19. Lim, W.Y.B., Ng, J.S., Nie, J., Hu, Q., Xiong, Z., Niyato, D., and Miao, C. (2022, January 16–20). Evolutionary Model Owner Selection for Federated Learning with Heterogeneous Privacy Budgets. Proceedings of the ICC 2022-IEEE International Conference on Communications, Seoul, Republic of Korea.
20. Community-structured evolutionary game for privacy protection in social networks10.1109/TIFS.2017.2758756 ↗
21. Abadi, M., Chu, A., Goodfellow, I., McMahan, H.B., Mironov, I., Talwar, K., and Zhang, L. (2016, January 24–28). Deep learning with differential privacy. Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, Vienna, Austria.10.1145/2976749.2978318 ↗
22. Yang, C., Qi, J., and Zhou, A. (2024, January 20–27). Wasserstein Differential Privacy. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.
23. Triastcyn, A., and Faltings, B. (2019, January 9–12). Federated learning with bayesian differential privacy. Proceedings of the 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, CA, USA.10.1109/BigData47090.2019.9005465 ↗
24. Triastcyn, A., and Faltings, B. (2020, January 13–18). Bayesian differential privacy for machine learning. Proceedings of the International Conference on Machine Learning, PMLR, Virtual.
25. Gaussian differential privacy10.1111/rssb.12454 ↗
26. Deep learning with gaussian differential privacy
27. Chuanxin, Z., Yi, S., and Degang, W. (2020, January 17–19). Federated learning with Gaussian differential privacy. Proceedings of the 2020 2nd International Conference on Robotics, Intelligent Control and Artificial Intelligence, Shanghai, China.10.1145/3438872.3439097 ↗
28. The algorithmic foundations of differential privacy10.1561/0400000042 ↗
29. Loss-privacy tradeoff in federated edge learning10.1109/JSTSP.2022.3161786 ↗
30. ur Rehman, M.H., Salah, K., Damiani, E., and Svetinovic, D. (2020, January 27–30). Towards blockchain-based reputation-aware federated learning. Proceedings of the IEEE INFOCOM 2020-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), Beijing, China.10.1109/INFOCOMWKSHPS50562.2020.9163027 ↗
31. Federated learning with fair incentives and robust aggregation for UAV-aided crowdsensing10.1109/TNSE.2021.3138928 ↗
32. Deepchain: Auditable and privacy-preserving deep learning with blockchain-based incentive
33. Zou, Y., Feng, S., Niyato, D., Jiao, Y., Gong, S., and Cheng, W. (2019, January 14–17). Mobile device training strategies in federated learning: An evolutionary game approach. Proceedings of the 2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), Atlanta, GA, USA.10.1109/iThings/GreenCom/CPSCom/SmartData.2019.00157 ↗
34. Cheng, Z., Wang, B., Pan, Y., and Liu, Y. (2023). Strategic Analysis of Participants in BCFL-Enabled Decentralized IoT Data Sharing. Mathematics, 11.10.3390/math11214520 ↗
35. Cloud federation formation using genetic and evolutionary game theoretical models10.1016/j.future.2019.10.008 ↗
36. When Federated Learning Meets Game Theory: A Cooperative Framework to Secure IIoT Applications on Edge Computing10.1109/TII.2022.3170347 ↗
37. Weibull, J.W. (1997). Evolutionary Game Theory, MIT Press.
38. Stable games and their dynamics10.1016/j.jet.2009.01.007 ↗