Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
129 tokens/sec
GPT-4o
28 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

On the Robustness of Graph Reduction Against GNN Backdoor (2407.02431v2)

Published 2 Jul 2024 in cs.LG and cs.CR

Abstract: Graph Neural Networks (GNNs) are gaining popularity across various domains due to their effectiveness in learning graph-structured data. Nevertheless, they have been shown to be susceptible to backdoor poisoning attacks, which pose serious threats to real-world applications. Meanwhile, graph reduction techniques, including coarsening and sparsification, which have long been employed to improve the scalability of large graph computational tasks, have recently emerged as effective methods for accelerating GNN training on large-scale graphs. However, the current development and deployment of graph reduction techniques for large graphs overlook the potential risks of data poisoning attacks against GNNs. It is not yet clear how graph reduction interacts with existing backdoor attacks. This paper conducts a thorough examination of the robustness of graph reduction methods in scalable GNN training in the presence of state-of-the-art backdoor attacks. We performed a comprehensive robustness analysis across six coarsening methods and six sparsification methods for graph reduction, under three GNN backdoor attacks against three GNN architectures. Our findings indicate that the effectiveness of graph reduction methods in mitigating attack success rates varies significantly, with some methods even exacerbating the attacks. Through detailed analyses of triggers and poisoned nodes, we interpret our findings and enhance our understanding of how graph reduction influences robustness against backdoor attacks. These results highlight the critical need for incorporating robustness considerations in graph reduction for GNN training, ensuring that enhancements in computational efficiency do not compromise the security of GNN systems.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. PoisonedGNN: Backdoor attack on graph neural networks-based hardware security systems. IEEE Trans. Comput. (2023).
  2. Lilas Alrahis and Ozgur Sinanoglu. 2023. Graph Neural Networks for Hardware Vulnerability Analysis—Can you Trust your GNN?. In 2023 IEEE 41st VLSI Test Symposium (VTS). IEEE, 1–4.
  3. Aleksandar Bojchevski and Stephan Günnemann. 2017. Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking. arXiv preprint arXiv:1707.03815 (2017).
  4. Aleksandar Bojchevski and Stephan Günnemann. 2018. Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking. arXiv:1707.03815 [stat.ML]
  5. NF-GNN: network flow graph neural networks for malware detection and classification. In Proceedings of the 33rd International Conference on Scientific and Statistical Database Management. 121–132.
  6. Unnoticeable backdoor attacks on graph neural networks. In Proceedings of the ACM Web Conference 2023. 2263–2273.
  7. Florian Dorfler and Francesco Bullo. 2012. Kron reduction of graphs with applications to electrical networks. IEEE Transactions on Circuits and Systems I: Regular Papers 60, 1 (2012), 150–163.
  8. A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 5376–5389.
  9. A fair comparison of graph neural networks for graph classification. arXiv preprint arXiv:1912.09893 (2019).
  10. Neural message passing for quantum chemistry. In International conference on machine learning. PMLR, 1263–1272.
  11. Structure-preserving sparsification methods for social networks. Social Network Analysis and Mining 6 (2016), 1–22.
  12. Inductive representation learning on large graphs. Advances in neural information processing systems 30 (2017).
  13. Open graph benchmark: Datasets for machine learning on graphs. Advances in neural information processing systems 33 (2020), 22118–22133.
  14. Scaling up graph neural networks via graph coarsening. In Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining. 675–684.
  15. George Karypis and Vipin Kumar. 1998. A fast and high quality multilevel scheme for partitioning irregular graphs. SIAM Journal on scientific Computing 20, 1 (1998), 359–392.
  16. Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).
  17. What is Twitter, a social network or a news media?. In Proceedings of the 19th international conference on World wide web. 591–600.
  18. GCN-GAN: A non-linear temporal link prediction model for weighted dynamic networks. In IEEE INFOCOM 2019-IEEE conference on computer communications. IEEE, 388–396.
  19. Graph evolution: Densification and shrinking diameters. ACM transactions on Knowledge Discovery from Data (TKDD) 1, 1 (2007), 2–es.
  20. A unified framework for data poisoning attack to graph-based semi-supervised learning. arXiv preprint arXiv:1910.14147 (2019).
  21. Survey on Graph Neural Network Acceleration: An Algorithmic Perspective. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22. 5521–5529.
  22. Andreas Loukas. 2019. Graph Reduction with Spectral and Cut Guarantees. J. Mach. Learn. Res. 20, 116 (2019), 1–42.
  23. Andreas Loukas and Pierre Vandergheynst. 2018. Spectrally approximating large graphs with smaller graphs. In International Conference on Machine Learning. PMLR, 3237–3246.
  24. NetworkKit. 2024. https://networkit.github.io/. Accessed: 2024-06-30.
  25. Relaxation-based coarsening and multiscale graph organization. Multiscale Modeling & Simulation 9, 1 (2011), 407–423.
  26. Local graph sparsification for scalable clustering. In Proceedings of the 2011 ACM SIGMOD International Conference on Management of data. 721–732.
  27. Collective classification in network data. AI magazine 29, 3 (2008), 93–93.
  28. Graph convolutional networks for computational drug development and discovery. Briefings in bioinformatics 21, 3 (2020), 919–935.
  29. Rethinking Graph Neural Networks for Anomaly Detection. In Proceedings of the 39th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, 21076–21089.
  30. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).
  31. Traffic flow prediction via spatial temporal graph neural network. In Proceedings of the web conference 2020. 1082–1092.
  32. Anti-money laundering in bitcoin: Experimenting with graph convolutional networks for financial forensics. arXiv preprint arXiv:1908.02591 (2019).
  33. Graph backdoor. In 30th USENIX Security Symposium (USENIX Security 21). 1523–1540.
  34. Graph neural networks in node classification: survey and evaluation. Machine Vision and Applications 33 (2022), 1–19.
  35. Scan: a structural clustering algorithm for networks. In Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining. 824–833.
  36. Hongxia Yang. 2019. Aligraph: A comprehensive graph neural network platform. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. 3165–3166.
  37. Gnn4tj: Graph neural networks for hardware trojan detection at register transfer level. In 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 1504–1509.
  38. Graph convolutional neural networks for web-scale recommender systems. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. 974–983.
  39. Graph contrastive backdoor attacks. In International Conference on Machine Learning. PMLR, 40888–40910.
  40. A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware. arXiv preprint arXiv:2306.14052 (2023).
  41. Backdoor attacks to graph neural networks. In Proceedings of the 26th ACM Symposium on Access Control Models and Technologies. 15–26.
  42. Adversarial attacks on neural networks for graph data. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. 2847–2856.
  43. Adversarial attacks on graph neural networks: Perturbations and their patterns. ACM Transactions on Knowledge Discovery from Data (TKDD) 14, 5 (2020), 1–31.
  44. Daniel Zügner and Stephan Günnemann. 2019. Adversarial Attacks on Graph Neural Networks via Meta Learning. In International Conference on Learning Representations.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now