Abstract
In the context of federated learning, the concept of federated unlearning has emerged, aiming to realize the “right to be forgotten”. The current research primarily focuses on designing unlearning techniques for clients “right to be forgotten”, it has often bypassed to consider the server’s authority to discard the client contribution without taking any consent from participating clients, we named it “right to forget”. These client contributions may contain adverse effects that could significantly impact global aggregation. In this research paper, we conduct a comprehensive review of previous studies related to federated unlearning and explore the server “right to forget” client’s contributions. We also introduce new taxonomies to classify and summarize the latest advancements in federated unlearning algorithms. Moreover, we take the first step to present the server right to forget (SRF), a novel unlearning methodology that enables the server to remove unreliable client contributions to improve global model accuracy. Experiments on two different kinds of datasets and models demonstrate the effectiveness of our method. We envision our effort as a first step toward the server’s right to forget the client’s contribution in the context of federated unlearning toward adherence to legal and ethical standards in a just and transparent manner.
Muntazir Mehdi, Amaad Hussain: Equally Contributed.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The unlearning condition is that the global model’s accuracy in the current round must drop below that in the previous round.
References
Voigt, Paul, von dem Bussche, Axel: The EU General Data Protection Regulation (GDPR): A Practical Guide. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-57959-7
Mantelero, A.: The EU proposal for a general data protection regulation and the roots of the ‘right to be forgotten’. Comput. Law & Secur. Rev. 29(3), 229–235 (2013)
Zaeem, R.N., Suzanne Barber, K.: The effect of the GDPR on privacy policies: recent progress and future promise. ACM Trans. Manag. Inf. Syst. (TMIS) 12(1), 1–20 (2020)
Ginart, A., Guan, M., Valiant, G., Zou, J.Y.: Making AI forget you: data deletion in machine learning. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Liu, G., Ma, X., Yang, Y., Wang, C., Liu, J.: Federated unlearning. arXiv preprint arXiv:2012.13891 (2020)
Kairouz, P., et al.: Advances and open problems in federated learning. Found. Trends® Mach. Learn. 14(1–2), 1–210 (2021)
Navia-Vázquez, A., Gutierrez-Gonzalez, D., Parrado-Hernández, E., Navarro-Abellan, J.J.: Distributed support vector machines. IEEE Tran. Neural Networks 17(4), 1091 (2006)
Ayush, K.T., Vikram, S.C., Murari, M., Mohan, K.: Deep regression unlearning. arXiv preprint arXiv:2210.08196 (2022)
Manaar, A., Hithem, L., Michail, M.: Get rid of your trail: remotely erasing backdoors in federated learning. arXiv preprint arXiv:2304.10638 (2023)
Nguyen, T.T., Huynh, T.T., Nguyen, P.L., Liew, A.W.-C., Yin, H., Nguyen, Q.H.V.: A survey of machine unlearning. arXiv preprint arXiv:2209.02299 (2022)
Liu, G., Ma, X., Yang, Y., Wang, C., Liu, J.,: FedEraser: enabling efficient client-level data removal from federated learning models. In: 2021 IEEE/ACM 29th International Symposium on Quality of Service (IWQOS), pp. 1–10. IEEE (2021)
Liu, Y., Xu, L., Yuan, X., Wang, C., Li, B.: The right to be forgotten in federated learning: an efficient realization with rapid retraining. In: IEEE INFOCOM 2022-IEEE Conference on Computer Communications, pp. 1749–1758. IEEE (2022)
Anisa, H., Swanand, K., Ambrish, R., Nathalie, B.: Federated unlearning: how to efficiently erase a client in FL? arXiv preprint arXiv:2207.05521 (2022)
Wu, C., Zhu, S., Mitra, P.: Federated unlearning with knowledge distillation. arXiv preprint arXiv:2201.09441 (2022)
Lucas, B., et al.: Machine unlearning. In: Proceedings of the 42nd IEEE Symposium on Security and Privacy, SP 2021, Washington, DC, USA. IEEE Computer Society (2021)
Stuart, L.P.: The california consumer privacy act: towards a European-style privacy regime in the united states. J. Tech. L. & Pol’y, 23, 68 (2018)
Yuan, W., Yin, H., Wu, F., Zhang, S., He, T., Wang, H.: Federated unlearning for on-device recommendation. In: Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, pp. 393–401 (2023)
Li, G., Shen, L., Sun, Y., Hu, Y., Hu, H., Tao, D.: Subspace based federated unlearning. arXiv preprint arXiv:2302.12448 (2023)
Liu, Y., Ma, Z., Liu, X., Ma, J.: Learn to forget: user-level memorization elimination in federated learning. arXiv preprint arXiv:2003.10933 (2020)
Leijie, W., Guo, S., Wang, J., Hong, Z., Zhang, J., Ding, Y.: Federated unlearning: guarantee the right of clients to forget. IEEE Network 36(5), 129–135 (2022)
Gao, X., et al.: VeriFi: towards verifiable federated unlearning. arXiv preprint arXiv:2205.12709 (2022)
Liu, Y., Ma, Z., Yang, Y., Liu, X., Ma, J., Ren, K.: RevFRF: enabling cross-domain random forest training with revocable federated learning. IEEE Trans. Dependable Secure Comput. 19(6), 3671–3685 (2021)
LeCun, Y.: The MNIST database of handwritten digits. http://yann.lecun.com/exdb/mnist/, (1998)
Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747 (2017)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Bano, H., Ameen, M., Mehdi, M., Hussain, A., Wang, P. (2024). Federated Unlearning and Server Right to Forget: Handling Unreliable Client Contributions. In: Santosh, K., et al. Recent Trends in Image Processing and Pattern Recognition. RTIP2R 2023. Communications in Computer and Information Science, vol 2027. Springer, Cham. https://doi.org/10.1007/978-3-031-53085-2_31
Download citation
DOI: https://doi.org/10.1007/978-3-031-53085-2_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53084-5
Online ISBN: 978-3-031-53085-2
eBook Packages: Computer ScienceComputer Science (R0)