Abstract
Privacy is a well-researched area in the context of Federated Learning. Typically, ensuring privacy means that individual data used for local training cannot be reconstructed by other local learners or a central server. Thus, it is the individual data points that should be private, but not the entire distribution of locally available data. In many cases, this makes sense because each data point comes from a different individual while all data points originate from a common global distribution. In this position paper, we address a more challenging task where the privacy of each local data distribution must be preserved. This is relevant for use cases where there is a one-to-one mapping from local learners to users, such as when each local learner is part of a personalized assistant on a smartphone. We provide a definition of this problem case, describe the challenges that need to be addressed, and formulate a possible approach to solve the problem.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Acar, A., Aksu, H., Uluagac, A.S., Conti, M.: A survey on homomorphic encryption schemes: theory and implementation. ACM Comput. Surv. 51(4), 1ā35 (2018)
Cheng, Y., Zhang, L., Li, A.: GFL: federated learning on non-IID data via privacy-preserving synthetic data. In: 2023 IEEE International Conference on Pervasive Computing and Communications, pp. 61ā70 (2023)
Dwork, C., McSherry, F., Nissim, K., Smith, A.: Calibrating noise to sensitivity in private data analysis. In: Halevi, S., Rabin, T. (eds.) TCC 2006. LNCS, vol. 3876, pp. 265ā284. Springer, Heidelberg (2006). https://doi.org/10.1007/11681878_14
Dwork, C., Roth, A.: The algorithmic foundations of differential privacy. Found. Trends Theor. Comput. Sci. 9(3ā4), 211ā407 (2014)
Evans, D., Kolesnikov, V., Rosulek, M.: A pragmatic introduction to secure multi-party computation. Found. Trends Priv. Secur. 2(2ā3), 70ā246 (2018)
Gentry, C.: Fully homomorphic encryption using ideal lattices. In: ACM Symposium on Theory of Computing, pp. 169ā178 (2009)
Gretton, A., Smola, A., Huag, J., Schmittfull, M., Bordwardt, K., Schƶlkopf, B.: Covariate shift by kernel mean matching. In: QuiƱonero, J., et al. (eds.) Dataset Shift in Machine Learning. MIT Press (2009)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Deep Learning and Representation Learning Workshop (2015)
Li, T., Sahu, A.K., Talwalkar, A., Smith, V.: Federated learning: challenges, methods, and future directions. IEEE Sig. Process. Mag. 37(3), 50ā60 (2020)
McMahan, B., Moore, E., Ramage, D., Hampson, S., y Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics, pp. 1273ā1282. PMLR (2017)
McMahan, B., Ramage, D., Talwar, K., Zhang, L.: Learning differentially private recurrent language models. In: 6th International Conference on Learning Representations, ICLR (2017)
Shen, T., et al.: Federated mutual learning. arXiv preprint arXiv:2006.16765 (2020)
Yao, A.C.: Protocols for secure computations. In: 23rd IEEE Annual Symposium on Foundations of Computer Science, pp. 160ā164 (1982)
Zhu, Z., Hong, J., Zhou, J.: Data-free knowledge distillation for heterogeneous federated learning. In: Proceedings of the 38th International Conference on Machine Learning 2021, vol. 139, pp. 12878ā12889. PMLR (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Stelldinger, P., Ibrahim, M.F.R. (2024). Local Distribution Privacy in Federated Learning. In: Kƶhler-BuĆmeier, M., Renz, W., Sudeikat, J. (eds) Intelligent Distributed Computing XVI. IDC 2023. Studies in Computational Intelligence, vol 1138. Springer, Cham. https://doi.org/10.1007/978-3-031-60023-4_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-60023-4_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-60022-7
Online ISBN: 978-3-031-60023-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)