Skip to main content

Advertisement

Springer Nature Link
Log in

A federated learning model based on filtering strategy

  • Manuscript
  • Published:
World Wide Web Aims and scope Submit manuscript

Abstract

With the increase of IoT terminals, data has also shown explosive growth in recent years. Due to the dispersion, low replication cost, and value aggregation of data, data owners are unwilling to share data. Therefore, it is difficult for them to use each other’s data for analysis or modeling, and the problem of data islands is serious. Federated learning can solve this problem. It uses the parameter data provided by different nodes to complete the training of the same global model, which greatly ensures the security and privacy of the data. However, if there are malicious nodes, the accuracy of global model training will be significantly reduced, and it will cause an unnecessary communication burden. Therefore, this paper proposes a federated learning model based on filtering strategy. The model filters three types of malicious nodes through the filtering algorithm to ensure the accuracy of the global model. The reward and punishment mechanism are used to reduce the weight of malicious participating nodes to have fewer opportunities to participate in training and reduce unnecessary communication overhead. The experiments show that the model has an excellent filtering effect on three types of malicious nodes.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12

Similar content being viewed by others

References

  1. Sestino, A., Prete, M.I., Piper, L., et al.: Internet of Things and Big Data as enablers for business digitalization strategies[J]. Technovation. 102173 (2020)

  2. Nižetić, S., Šolić, P., González-de, D.L.I., et al.: Internet of Things (IoT): Opportunities, issues, and challenges towards a smart and sustainable future[J]. J. Clean. Prod. 274, 122877 (2020)

    Article  Google Scholar 

  3. Wang, F.Y., Wang, Y.F.: Federated ecology: from federated data to federated intelligence[J]. Chin. J. Intell. Sci. Technol. 2(4), 305–313 (2020)

    Google Scholar 

  4. Xie, F., Bian, J.L., Wang, N., et al.: Application of federal studies in the field of artificial intelligence in power IoT[J]. China High Technol. Enterp. (23), 18–21 (2019)

  5. Xu, Y., Ren, J., Zhang, Y., et al.: Blockchain empowered arbitrable data auditing scheme for network storage as a service[J]. IEEE Trans. Serv. Comput. 13(2), 289–300 (2020)

    Google Scholar 

  6. Yang, Q., AI and Data Privacy Protection: The Way to Federated Learning[J]. J. Inform. Secur. Res. 5(11), 961–965 (2019)

    Google Scholar 

  7. Zhou, C.X., Sun, Y., Wang, D.G., et al.: Survey of Federated Learning research [J]. Chin. J. Netw. Inf. Secur. 1–16 (2021)

  8. Zhou, J., Fang, G.Y., Wu, N.: Survey on security and privacy-preserving in federated learning[J]. J. Xihua Univ. (Nat. Sci. Ed.) 39(4), 9–17 (2020)

    Google Scholar 

  9. Qiu, X.Y., Ye, Z.C., Cui, X.L., et al.: Survey of communication cost of federated Learning[J]. J. Comput. Appl. 1–11 (2021)

  10. Liu, C., Li, B., Vorobeychik, Y., et al.: Robust linear regression against training data poisoning[C]. Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security, 91–102 (2017)

  11. Cao, D., Chang, S., Lin, Z., et al.: Understanding distributed poisoning attack in federated learning[C]. 2019 IEEE 25th International Conference on Parallel and Distributed Systems (ICPADS). IEEE, 233–239 (2019)

  12. Zhang, J., Wu, D., Liu, C., et al.: Defending poisoning attacks in federated learning via adversarial training method[C]. International Conference on Frontiers in Cyber Security. Springer, Singapore, 83–94 (2020)

  13. Konečný, J., McMahan, H.B., Yu, F.X., et al.: Federated learning: Strategies for improving communication efficiency[J]. arXiv preprint arXiv:1610.05492 (2016)

  14. Yang, Q., Liu, Y., Chen, T., et al.: Federated machine learning: Concept and applications[J]. ACM Trans. Intell. Syst. Technol. (TIST) 10(2), 1–19 (2019)

    Article  Google Scholar 

  15. Xu, Y., Bhuiyan, M.Z.A., Wang, T., et al.: C-fDRL: Context-aware privacy-preserving offloading through federated deep reinforcement learning in cloud-enabled IoT[J]. IEEE Trans. Industr. Inf. (2022). https://doi.org/10.1109/TII.2022.3149335

    Article  Google Scholar 

  16. Xiao, H., Xiao, H., Eckert, C.: Adversarial label flips attack on support vector machines[C]. ECAI. 870–875 (2012)

  17. Wei, X.L., Zhang, Z.Y., Song, B., et al.: Social networks cross-platform malicious user detection method based on vertical federated learning[J/OL]. J. Chin. Comput. Syst. 1–9 (2021)

  18. Li, S., Cheng, Y., Liu, Y., et al.: Abnormal client behavior detection in federated learning[J]. arXiv preprint arXiv:1910.09933 (2019)

  19. Chen, Y., Luo, F., Li, T., et al.: A training-integrity privacy-preserving federated learning scheme with trusted execution environment[J]. Inf. Sci. 522, 69–79 (2020)

    Article  Google Scholar 

  20. Baracaldo, N., Chen, B., Ludwig, H., et al.: Mitigating poisoning attacks on machine learning models: A data provenance-based approach[C]. Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security, 103–110 (2017)

  21. Fung, C., Yoon, C.J.M., Beschastnikh, I.: Mitigating sybils in federated learning poisoning[J]. arXiv preprint arXiv:1808.04866 (2018)

  22. Singh, A.K., Blanco-Justicia, A., Domingo-Ferrer, J., et al.: Fair detection of poisoning attacks in federated learning[C]. 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 224–229 (2020)

  23. Zhu, X., Li, H., Yu, Y.: Blockchain-based privacy preserving deep learning[C]. International Conference on Information Security and Cryptology. Springer, Cham, 370–383 (2018)

  24. McMahan, B., Moore, E., Ramage, D., et al.: Communication-efficient learning of deep networks from decentralized data[C]. Artificial intelligence and statistics. PMLR, 1273–1282 (2017)

  25. Li, T., Sahu, A.K., Zaheer, M., et al.: Federated optimization in heterogeneous networks[J]. arXiv preprint arXiv:1812.06127 (2018)

  26. Liu, W., Chen, L., Chen, Y., et al.: Accelerating federated learning via momentum gradient descent[J]. IEEE Trans. Parallel Distrib. Syst. 31(8), 1754–1766 (2020)

    Article  Google Scholar 

  27. Jiang, J., Hu, L., Hu, C., et al.: BACombo—Bandwidth-aware decentralized federated learning[J]. Electronics 9(3), 440 (2020)

    Article  Google Scholar 

  28. Reisizadeh, A., Mokhtari, A., Hassani, H., et al.: Fedpaq: A communication-efficient federated learning method with periodic averaging and quantization[C]. International Conference on Artificial Intelligence and Statistics. PMLR, 2021–2031 (2020)

  29. Xu, Y., Liu, Z., Zhang, C., et al.: Blockchain-based trustworthy energy dispatching approach for high renewable energy penetrated power system[J]. IEEE Internet Things J. (2021). https://doi.org/10.1109/JIOT.2021.3117924

    Article  Google Scholar 

  30. Sun, M., Li, J., et al.: Research on federated learning and its security issues for load forecasting[C]. The 10th International Conference on Intelligent Computing and Applications (ICICA 2021), Melbourne, Australia during June 25–27 (2021)

  31. Goyal, V., Pandey, O., Sahai, A., et al.: Attribute-based encryption for fine-grained access control of encrypted data[C]. Proceedings of the 13th ACM conference on Computer and communications security, 89–98 (2006)

  32. Jin, W., Li, Z.J., Wei, L.S., et al.: The improvements of BP neural network learning algorithm[C]. WCC 2000-ICSP 2000. 5th international conference on signal processing proceedings. 16th world computer congress 2000. IEEE, 3, 1647–1649 (2000)

Download references

Author information

Authors and Affiliations

  1. School of Control and Computer Engineering, North China Electric Power University, 2 Beinong Road, 102206, Beijing, China

    Jingchen Yan, Mingyu Sun, Zhe Du, Xin Tong & Jianbin Li

  2. First System Department, North China Institute of Computing Technology, 269 Beijing North Fourth Ring Road, 100083, Beijing, China

    Jingchen Yan

Authors
  1. Jingchen Yan
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Mingyu Sun
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Zhe Du
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Xin Tong
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Jianbin Li
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Jianbin Li.

Ethics declarations

Conflict of interest

No conflict of interest exits in the submission of this manuscript, and manuscript is approved by all authors for publication. I would like to declare on behalf of my co-authors that the work described was original research that has not been published previously, and not under consideration for publication elsewhere. All the authors listed have approved the manuscript that is enclosed.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yan, J., Sun, M., Du, Z. et al. A federated learning model based on filtering strategy. World Wide Web 26, 1031–1053 (2023). https://doi.org/10.1007/s11280-022-01074-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11280-022-01074-7

Keywords