Abstract
Federated learning is widely used in mobile computing, the Internet of Things, and other scenarios due to its distributed and privacy-preserving nature. It allows mobile devices to train machine learning models collaboratively without sharing their local private data. However, during the model aggregation phase, federated learning is vulnerable to poisoning attacks carried out by malicious users. Furthermore, due to the heterogeneity of network status, communication conditions, hardware, and other factors, users are at high risk of offline, which allows attackers to fake virtual participants and increase the damage of poisoning. Unlike existing work, we focus on the more general case of untargeted poisoning attacks. In this paper, we propose novel sybil-based untargeted data poisoning attacks in federated learning (SPoiL), in which malicious users corrupt the performance of the global model by modifying the training data and increasing the probability of poisoning by virtualizing several sybil nodes. Finally, we validate the superiority of our attack approach through experiments across the commonly used datasets.
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
References
Bonawitz, K., et al.: Towards federated learning at scale: system design. Proc. Mach. Learn. Syst. 1, 374–388 (2019). https://proceedings.mlsys.org/paper/2019/hash/bd686fd640be98efaae0091fa301e613-Abstract.html
Bonawitz, K., et al.: Practical secure aggregation for privacy-preserving machine learning. In: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, CCS 2017, pp. 1175–1191. Association for Computing Machinery, New York, NY, USA (2017). https://doi.org/10.1145/3133956.3133982
Cao, D., Chang, S., Lin, Z., Liu, G., Sun, D.: Understanding distributed poisoning attack in federated learning. In: 2019 IEEE 25th International Conference on Parallel and Distributed Systems (ICPADS), pp. 233–239. IEEE (2019). https://doi.org/10.1109/ICPADS47876.2019.00042
Cao, D., Chang, S., Lin, Z., Liu, G., Sun, D.: Understanding distributed poisoning attack in federated learning. In: 2019 IEEE 25th International Conference on Parallel and Distributed Systems (ICPADS), pp. 233–239 (2019). https://doi.org/10.1109/ICPADS47876.2019.00042
Douceur, J.R.: The Sybil attack. In: Druschel, P., Kaashoek, F., Rowstron, A. (eds.) IPTPS 2002. LNCS, vol. 2429, pp. 251–260. Springer, Heidelberg (2002). https://doi.org/10.1007/3-540-45748-8_24
Jamali-Rad, H., Abdizadeh, M., Singh, A.: Federated learning with taskonomy for non-IID data. IEEE Trans. Neural Netw. Learn. Syst., 1–12 (2022). https://doi.org/10.1109/TNNLS.2022.3152581
Kaggle fake news dataset. https://www.kaggle.com/competitions/fake-news/data
Kourtellis, N., Katevas, K., Perino, D.: Flaas: federated learning as a service. In: Proceedings of the 1st Workshop on Distributed Machine Learning, DistributedML 2020, pp. 7–13. Association for Computing Machinery, New York, NY, USA (2020). https://doi.org/10.1145/3426745.3431337
Krešňáková, V.M., Sarnovský, M., Butka, P.: Deep learning methods for fake news detection. In: 2019 IEEE 19th International Symposium on Computational Intelligence and Informatics and 7th IEEE International Conference on Recent Achievements in Mechatronics, Automation, Computer Sciences and Robotics (CINTI-MACRo), pp. 000143–000148 (2019). https://doi.org/10.1109/CINTI-MACRo49179.2019.9105317
McMahan, B., Ramage, D.: Federated Learning: Collaborative Machine Learning without Centralized Training Data (2017). https://ai.googleblog.com/2017/04/federated-learning-collaborative.html
Nuding, F., Mayer, R.: Data poisoning in sequential and parallel federated learning. In: Proceedings of the 2022 ACM on International Workshop on Security and Privacy Analytics, IWSPA 2022, pp. 24–34. Association for Computing Machinery, New York, NY, USA (2022). https://doi.org/10.1145/3510548.3519372
Sagar, S., Li, C.S., Loke, S.W., Choi, J.: Poisoning attacks and defenses in federated learning: a survey. arXiv (Jan 2023). https://doi.org/10.48550/arXiv.2301.05795
Sharma, P.K., Park, J.H., Cho, K.: Blockchain and federated learning-based distributed computing defence framework for sustainable society. Sustain. Cities Soc. 59, 102220 (2020)
Shejwalkar, V., Houmansadr, A., Kairouz, P., Ramage, D.: Back to the drawing board: a critical evaluation of poisoning attacks on production federated learning. In: 2022 IEEE Symposium on Security and Privacy (SP), pp. 1354–1371 (2022). https://doi.org/10.1109/SP46214.2022.9833647
Shejwalkar, V., Houmansadr, A., Kairouz, P., Ramage, D.: Back to the drawing board: a critical evaluation of poisoning attacks on production federated learning. In: 2022 IEEE Symposium on Security and Privacy (SP), pp. 1354–1371. IEEE (2022). https://doi.org/10.1109/SP46214.2022.9833647
Tahir, M., Ali, M.I.: On the performance of federated learning algorithms for IoT. IoT 3(2), 273–284 (2022)
Tolpegin, V., Truex, S., Gursoy, M.E., Liu, L.: Data poisoning attacks against federated learning systems. In: Chen, L., Li, N., Liang, K., Schneider, S. (eds.) ESORICS 2020. LNCS, vol. 12308, pp. 480–501. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58951-6_24
Wang, H., Kaplan, Z., Niu, D., Li, B.: Optimizing federated learning on non-IID data with reinforcement learning. In: IEEE INFOCOM 2020-IEEE Conference on Computer Communications, pp. 1698–1707. IEEE (2020)
Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., Chandra, V.: Federated learning with non-IID data. arXiv preprint arXiv:1806.00582 (2018)
Zhou, X., Xu, M., Wu, Y., Zheng, N.: Deep model poisoning attack on federated learning. Future Internet 13(3), 73 (2021). https://doi.org/10.3390/fi13030073, https://www.mdpi.com/1999-5903/13/3/73
Acknowledgment
This work was partially supported by JSPS Grant-in-Aid for Scientific Research (C) 23K11103 and NEC C &C Foundation under Grants for Researchers.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lian, Z., Zhang, C., Nan, K., Su, C. (2023). SPoiL: Sybil-Based Untargeted Data Poisoning Attacks in Federated Learning. In: Li, S., Manulis, M., Miyaji, A. (eds) Network and System Security. NSS 2023. Lecture Notes in Computer Science, vol 13983. Springer, Cham. https://doi.org/10.1007/978-3-031-39828-5_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-39828-5_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-39827-8
Online ISBN: 978-3-031-39828-5
eBook Packages: Computer ScienceComputer Science (R0)