Abstract
As a distributed machine learning framework, federated learning enables a multitude of participants to train a joint model privately by keeping training data locally. The federated learning is emerging as a promising alternative to solve data privacy protection, but it has been proven that federated learning is vulnerable to attacks from malicious clients, especially Byzantine attackers sending poisoned parameters during the training phase. To address this problem, several aggregation approaches against Byzantine failures have been proposed. However, these existing aggregation methods are only of limited utility in the setting of privacy protection. This paper proposes a privacy-preserving and Byzantine-robust federated learning framework (PPBR-FL) which achieves the objective to satisfy privacy and robustness simultaneously. We use the local differential privacy mechanism to realize privacy protection for the clients and propose a Byzantine-robust aggregation rule named as TPM (Trimmed Padding Mean) to realize robustness. Extensive experiments on two benchmark datasets demonstrate that the TPM outperforms the classical aggregation approaches in terms of robustness and privacy. When less than half of the workers are Byzantine attackers, the final global model not only achieves satisfactory performance against Byzantine attack, but also provide privacy protection on parameters to prevent privacy disclosure.
This work is financed by “The project of Key Laboratory in Software Engineering of Yunnan Province (No. 2020SE305, 2020SE402)”.
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
Similar content being viewed by others
References
Bagdasaryan, E., Veit, A., Hua, Y., Estrin, D., Shmatikov, V.: How to backdoor federated learning. In: International Conference on Artificial Intelligence and Statistics, pp. 2938–2948. PMLR (2020)
Bassily, R., Nissim, K., Stemmer, U., Thakurta, A.: Practical locally private heavy hitters. J. Mach. Learn. Res. 21, 1–16 (2020)
Bhowmick, A., Duchi, J., Freudiger, J., Kapoor, G., Rogers, R.: Protection against reconstruction and its applications in private federated learning. arXiv preprint arXiv:1812.00984 (2018)
Blanchard, P., El Mhamdi, E.M., Guerraoui, R., Stainer, J.: Machine learning with adversaries: Byzantine tolerant gradient descent. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 118–128 (2017)
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. 265–284. Springer, Heidelberg (2006). https://doi.org/10.1007/11681878_14
Dwork, C., Roth, A., et al.: The algorithmic foundations of differential privacy. Found. Trends Theor. Comput. Sci. 9(3–4), 211–407 (2014)
Geyer, R.C., Klein, T., Nabi, M.: Differentially private federated learning: a client level perspective. arXiv preprint arXiv:1712.07557 (2017)
Li, L., Xu, W., Chen, T., Giannakis, G.B., Ling, Q.:RSA: byzantine-robust stochastic aggregation methods for distributed learning from heterogeneous datasets. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 33, pp. 1544–1551 (2019)
Li, S., Cheng, Y., Wang, W., Liu, Y., Chen, T.: Learning to detect malicious clients for robust federated learning. arXiv preprint arXiv:2002.00211 (2020)
Ma, C., et al.: On safeguarding privacy and security in the framework of federated learning. IEEE Netw. 34(4), 242–248 (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. 1273–1282. PMLR (2017)
McMahan, H.B., Moore, E., Ramage, D., y Arcas, B.A.: Federated learning of deep networks using model averaging. arXiv preprint arXiv:1602.05629 (2016)
Melis, L., Song, C., De Cristofaro, E., Shmatikov, V.: Inference attacks against collaborative learning. arXiv preprint arXiv:1805.04049 (2018)
Melis, L., Song, C., De Cristofaro, E., Shmatikov, V.: Exploiting unintended feature leakage in collaborative learning. In: 2019 IEEE Symposium on Security and Privacy (SP), pp. 691–706. IEEE (2019)
Naseri, M., Hayes, J., De Cristofaro, E.: Toward robustness and privacy in federated learning: experimenting with local and central differential privacy. arXiv preprint arXiv:2009.03561 (2020)
Qiu, H., Qiu, M., Lu, Z.: Selective encryption on ECG data in body sensor network based on supervised machine learning. Inf. Fusion 55, 59–67 (2020)
Qiu, M., Gai, K., Xiong, Z.: Privacy-preserving wireless communications using bipartite matching in social big data. Fut. Gener. Comput. Syst. 87, 772–781 (2018)
Sun, Z., Kairouz, P., Suresh, A.T., McMahan, H.B.: Can you really backdoor federated learning? arXiv preprint arXiv:1911.07963 (2019)
Wang, S., et al.: Local differential private data aggregation for discrete distribution estimation. IEEE Trans. Parallel Distrib. Syst. 30(9), 2046–2059 (2019)
Wei, K., et al.: User-level privacy-preserving federated learning: analysis and performance optimization. IEEE Trans. Mob. Comput. 99, 1-1 (2021)
Wu, Z., Ling, Q., Chen, T., Giannakis, G.B.: Federated variance-reduced stochastic gradient descent with robustness to byzantine attacks. IEEE Trans. Signal Process. 68, 4583–4596 (2020)
Xie, C., Koyejo, O., Gupta, I.: Generalized byzantine-tolerant sgd. arXiv preprint arXiv:1802.10116 (2018)
Yin, D., Chen, Y., Kannan, R., Bartlett, P.: Byzantine-robust distributed learning: Towards optimal statistical rates. In: International Conference on Machine Learning, pp. 5650–5659. PMLR (2018)
Yu, L., Liu, L., Pu, C., Gursoy, M.E., Truex, S.: Differentially private model publishing for deep learning. In: 2019 IEEE Symposium on Security and Privacy (SP), pp. 332–349. IEEE (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lin, Y. et al. (2022). PPBR-FL: A Privacy-Preserving and Byzantine-Robust Federated Learning System. In: Memmi, G., Yang, B., Kong, L., Zhang, T., Qiu, M. (eds) Knowledge Science, Engineering and Management. KSEM 2022. Lecture Notes in Computer Science(), vol 13370. Springer, Cham. https://doi.org/10.1007/978-3-031-10989-8_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-10989-8_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-10988-1
Online ISBN: 978-3-031-10989-8
eBook Packages: Computer ScienceComputer Science (R0)