Abstract
Graph neural networks can learn graph structure data directly and mine its information, which can be used in drug research and development, financial fraud prevention, and other fields. The existing research shows that the graph neural network is lacking robustness and is vulnerable to attack by adversarial examples. At present, there are two problems in the generation of confrontation examples for graph neural networks. One is that the properties of graph structure are not fully used to describe the antagonistic examples, the other is that the gradient calculation is linked with the loss function and not directly linked with the properties of graph structure, which leads to excessive search space. To solve these two problems, this paper proposes a graph structure data confrontation example generation scheme based on graph theory measurement. In this paper, the average distance and clustering coefficient is used as the basis for each step of disturbance, and the counterexamples are generated under the premise of keeping the data characteristics. Experimental results on small-world networks and random graphs show that, compared with the previous methods, the proposed method makes full use of the nature of graph structure, does not need complex derivation, and takes less time to generate confrontation examples, which can meet the needs of iterative development.
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
O’Shea, K., Nash, R.: An introduction to convolutional neural networks. arXiv preprint arXiv:1511.08458 (2015)
Lipton, Z.C., Berkowitz, J., Elkan, C.: A critical review of recurrent neural networks for sequence learning. arXiv preprint arXiv:1506.00019 (2015)
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., Philip, S.Y.: A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32(1), 4–24 (2020)
Yu, B., Yin, H., Zhu, Z.: Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. arXiv preprint arXiv:1709.04875 (2017)
Li, H., Liu, J., Wu, K., Yang, Z., Liu, R.W., Xiong, N.: Spatio-temporal vessel trajectory clustering based on data mapping and density. IEEE Access 6, 58939–58954 (2018)
He, R., Xiong, N., Yang, L.T., Park, J.H.: Using multi-modal semantic association rules to fuse keywords and visual features automatically for web image retrieval. Inf. Fusion 12(3), 223–230 (2011)
Weber, M., et al.: Anti-money laundering in bitcoin: Experimenting with graph convolutional networks for financial forensics. arXiv preprint arXiv:1908.02591 (2019)
Shaham, U., Yamada, Y., Negahban, S.: Understanding adversarial training: Increasing local stability of neural nets through robust optimization. arXiv preprint arXiv:1511.05432 (2015)
Di, Z., Wu, J.: Complex network research from statistical physics. PhD thesis (2004)
Wang, G.C.X., Li, X.: Complex Network Theory and Its Applications. Tsinghua University Press Co., Ltd., Beijing (2006)
Guangrong, C., Xiaofan, W., Li, X.: Introduction to Network Science, vol. 6. Higher Education Press, Beijing (2012)
Wang, Z., Li, T., Xiong, N., Pan, Y.: A novel dynamic network data replication scheme based on historical access record and proactive deletion. J. Supercomput. 62(1), 227–250 (2012)
Guo, W., Xiong, N., Vasilakos, A.V., Chen, G., Cheng, H.: Multi-source temporal data aggregation in wireless sensor networks. Wirel. Pers. Commun. 56(3), 359–370 (2011)
Yao, Y., Xiong, N., Park, J.H., Ma, L., Liu, J.: Privacy-preserving max/min query in two-tiered wireless sensor networks. Comput. Math. Appl. 65(9), 1318–1325 (2013)
Zhang, Q., Zhou, C., Tian, Y.-C., Xiong, N., Qin, Y., Bowen, H.: A fuzzy probability bayesian network approach for dynamic cybersecurity risk assessment in industrial control systems. IEEE Trans. Ind. Inf. 14(6), 2497–2506 (2017)
Mou, W., Tan, L., Xiong, N.: A structure fidelity approach for big data collection in wireless sensor networks. Sensors 15(1), 248–273 (2015)
Huang, S., Liu, A., Zhang, S., Wang, T., Xiong, N.N.: BD-VTE: a novel baseline data based verifiable trust evaluation scheme for smart network systems. IEEE Trans. Netw. Sci. Eng. (2020)
Yin, J., Lo, W., Deng, S., Li, Y., Zhaohui, W., Xiong, N.: Colbar: a collaborative location-based regularization framework for qos prediction. Inf. Sci. 265, 68–84 (2014)
Wan, Z., Xiong, N., Ghani, N., Vasilakos, A.V., Zhou, L.: Adaptive unequal protection for wireless video transmission over ieee 802.11 e networks. Multimed. Tools Appl. 72(1), 541–571 (2014)
Qu, Y., Xiong, N.: RFH: a resilient, fault-tolerant and high-efficient replication algorithm for distributed cloud storage. In: 2012 41st International Conference on Parallel Processing, pp. 520–529. IEEE (2012)
Gai, K., Qiu, M.: Reinforcement learning-based content-centric services in mobile sensing. IEEE Netw. 32(4), 34–39 (2018)
Gai, K., Qiu, M.: Optimal resource allocation using reinforcement learning for iot content-centric services. Appl. Soft Comput. 70, 12–21 (2018)
Gai, K., Qiu, M., Zhao, H., Sun, X.: Resource management in sustainable cyber-physical systems using heterogeneous cloud computing. IEEE Trans. Sustain. Comput. 3(2), 60–72 (2017)
Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)
Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z.B., Swami, A.: The limitations of deep learning in adversarial settings. In: 2016 IEEE European Symposium on Security and Privacy (EuroS&P), pp. 372–387. IEEE (2016)
Baluja, S., Fischer, I.: Adversarial transformation networks: Learning to generate adversarial examples. arXiv preprint arXiv:1703.09387 (2017)
Moosavi-Dezfooli, S.M., Fawzi, A., Frossard, P.: Deepfool: a simple and accurate method to fool deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2574–2582 (2016)
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)
Bojchevski, A., Günnemann, S.: Adversarial attacks on node embeddings via graph poisoning. In: International Conference on Machine Learning, pp. 695–704. PMLR (2019)
Perozzi, B., Al-Rfou, R., Skiena, S.: Deepwalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 701–710 (2014)
Gaitonde, J., Kleinberg, J., Tardos, E.: Adversarial perturbations of opinion dynamics in networks. In: Proceedings of the 21st ACM Conference on Economics and Computation, pp. 471–472 (2020)
Dai, H., et al.: Adversarial attack on graph structured data. In: International Conference on Machine Learning, pp. 1115–1124. PMLR (2018)
Sun, M., et al.: Data poisoning attack against unsupervised node embedding methods. arXiv preprint arXiv:1810.12881 (2018)
Chen, J., Shi, Z., Wu, Y., Xu, X., Zheng, H.: Link prediction adversarial attack. arXiv preprint arXiv:1810.01110 (2018)
Yu, S., Zheng, J., Chen, J., Xuan, Q., Zhang, Q.: Unsupervised euclidean distance attack on network embedding. In: 2020 IEEE Fifth International Conference on Data Science in Cyberspace (DSC), pp. 71–77. IEEE (2020)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. Adv. Neural Inf. Process. Syst. 30 (2017)
Kleinberg, J.: The small-world phenomenon: an algorithmic perspective. In: Proceedings of the Thirty-Second Annual ACM Symposium on Theory of Computing, pp. 163–170 (2000)
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
He, W., Lu, M., Zheng, Y., Xiong, N.N. (2022). Research on Graph Structure Data Adversarial Examples Based on Graph Theory Metrics. In: Qiu, M., Gai, K., Qiu, H. (eds) Smart Computing and Communication. SmartCom 2021. Lecture Notes in Computer Science, vol 13202. Springer, Cham. https://doi.org/10.1007/978-3-030-97774-0_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-97774-0_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-97773-3
Online ISBN: 978-3-030-97774-0
eBook Packages: Computer ScienceComputer Science (R0)