Skip to main content

Disttack: Graph Adversarial Attacks Toward Distributed GNN Training

  • Conference paper
  • First Online:
Euro-Par 2024: Parallel Processing (Euro-Par 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14802))

Included in the following conference series:

  • 653 Accesses

Abstract

Graph Neural Networks (GNNs) have emerged as potent models for graph learning. Distributing the training process across multiple computing nodes is the most promising solution to address the challenges of ever-growing real-world graphs. However, current adversarial attack methods on GNNs neglect the characteristics and applications of the distributed scenario, leading to suboptimal performance and inefficiency in attacking distributed GNN training.

In this study, we introduce Disttack, the first framework of adversarial attacks for distributed GNN training that leverages the characteristics of frequent gradient updates in a distributed system. Specifically, Disttack corrupts distributed GNN training by injecting adversarial attacks into one single computing node. The attacked subgraphs are precisely perturbed to induce an abnormal gradient ascent in backpropagation, disrupting gradient synchronization between computing nodes and thus leading to a significant performance decline of the trained GNN. We evaluate Disttack on four large real-world graphs by attacking five widely adopted GNNs. Compared with the state-of-the-art attack method, experimental results demonstrate that Disttack amplifies the model accuracy degradation by 2.75\(\times \) and achieves speedup by 17.33\(\times \) on average while maintaining unnoticeability.

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

Access this chapter

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

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    Open-sourced at https://github.com/zhangyxrepo/Disttack.

References

  1. Chen, Y., et al.: Understanding and improving graph injection attack by promoting unnoticeability. arXiv preprint arXiv:2202.08057 (2022)

  2. Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, vol. 30 (2017)

    Google Scholar 

  3. Jia, Z., Lin, S., Gao, M., Zaharia, M., Aiken, A.: Improving the accuracy, scalability, and performance of graph neural networks with ROC. Proc. Mach. Learn. Syst. 2, 187–198 (2020)

    Google Scholar 

  4. Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)

  5. Li, J., Xie, T., Chen, L., Xie, F., He, X., Zheng, Z.: Adversarial attack on large scale graph. IEEE Trans. Knowl. Data Eng. 35(1), 82–95 (2021)

    Google Scholar 

  6. Lin, H., Yan, M., Ye, X., Fan, D., Pan, S., Xie, Y.: A comprehensive survey on distributed training of graph neural networks. Proc. IEEE (2023)

    Google Scholar 

  7. Ma, L., Yang, Z., Miao, Y., Xue, J., et al.: Neugraph: parallel deep neural network computation on large graphs. In: 2019 USENIX Annual Technical Conference (USENIX ATC 2019) (2019)

    Google Scholar 

  8. Mosca, P., Zhang, Y., Xiao, Z., Wang, Y., et al.: Cloud security: services, risks, and a case study on amazon cloud services. Int. Commun. Netw. Syst. Sci. 7(12), 529 (2014)

    Google Scholar 

  9. Shao, Y., et al.: Distributed graph neural network training: a survey. ACM Comput. Surv. 56(8), 1–39 (2022)

    Article  Google Scholar 

  10. Sun, L., et al.: Adversarial attack and defense on graph data: a survey. IEEE Trans. Knowl. Data Eng. 35(8), 7693–7711 (2022)

    Google Scholar 

  11. Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)

  12. Wang, K., Shen, Z., Huang, C., Wu, C.H., Dong, Y., Kanakia, A.: Microsoft academic graph: when experts are not enough. Quant. Sci. Stud. 1(1), 396–413 (2020)

    Article  Google Scholar 

  13. Waniek, M., Michalak, T.P., Wooldridge, M.J., Rahwan, T.: Hiding individuals and communities in a social network. Nat. Hum. Behav. 2(2), 139–147 (2018)

    Article  Google Scholar 

  14. West, D.B., et al.: Introduction to graph theory, vol. 2 (2001)

    Google Scholar 

  15. Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., Weinberger, K.: Simplifying graph convolutional networks. In: International Conference on Machine Learning, pp. 6861–6871. PMLR (2019)

    Google Scholar 

  16. Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 (2018)

  17. Zeng, H., Zhou, H., Srivastava, A., Kannan, R., Prasanna, V.: Graphsaint: graph sampling based inductive learning method. arXiv preprint arXiv:1907.04931 (2019)

  18. Zhu, R., Zhao, K., Yang, H., Lin, W., Zhou, C., et al.: Aligraph: a comprehensive graph neural network platform. arXiv preprint arXiv:1902.08730 (2019)

  19. Zügner, D., Akbarnejad, A., Günnemann, S.: Adversarial attacks on neural networks for graph data. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2847–2856 (2018)

    Google Scholar 

  20. Zügner, D., Borchert, O., Akbarnejad, A., Günnemann, S.: Adversarial attacks on graph neural networks: perturbations and their patterns. ACM Trans. Knowl. Discov. Data (TKDD) 14(5), 1–31 (2020)

    Article  Google Scholar 

Download references

Acknowledgement

This work was supported by National Key Research and Development Program (Grant No. 2023YFB4502305), the National Natural Science Foundation of China (Grant No. 62202451), CAS Project for Young Scientists in Basic Research (Grant No. YSBR-029), and CAS Project for Youth Innovation Promotion Association.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Mingyu Yan .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Zhang, Y. et al. (2024). Disttack: Graph Adversarial Attacks Toward Distributed GNN Training. In: Carretero, J., Shende, S., Garcia-Blas, J., Brandic, I., Olcoz, K., Schreiber, M. (eds) Euro-Par 2024: Parallel Processing. Euro-Par 2024. Lecture Notes in Computer Science, vol 14802. Springer, Cham. https://doi.org/10.1007/978-3-031-69766-1_21

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-69766-1_21

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-69765-4

  • Online ISBN: 978-3-031-69766-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics