Abstract
Graph learning (GL) models have been applied in various predictive tasks on graph data. But, similarly to other machine learning models, GL models are also vulnerable to adversarial attacks. As a powerful attack method on graphs, spectral attack jeopardizes the eigenvalues or eigenvectors of the graph topology-related matrices (e.g., graph adjacency matrix and graph Laplacian matrix) due to their inherent connections to certain structural properties of the underlying graph. However, most existing spectral attack methods focus on damaging the global graph structural properties and can hardly perform effective attacks on a target node. In this paper, we propose a novel targeted spectral attack method that can perform model-agnostic attacks effectively on the local structural properties of a target node. First, we define a novel node-specific metric—spectral density distance, which measures the difference of the local structural properties for the same target node between two different graph topologies. Then, we conduct attacks by maximizing the spectral density distance between the graphs before and after perturbation. Additionally, we also develop an effective strategy to improve attack efficiency by using the eigenvalue perturbation theory. Experimental results on three widely used datasets demonstrate the effectiveness of our proposed approach.
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
Similar content being viewed by others
References
Bojchevski, A., Günnemann, S.: Adversarial attacks on node embeddings via graph poisoning. In: International Conference on Machine Learning, pp. 695–704. PMLR (2019)
Chang, H., et al.: A restricted black-box adversarial framework towards attacking graph embedding models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 3389–3396 (2020)
Dong, K., Benson, A.R., Bindel, D.: Network density of states. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1152–1161 (2019)
Fiedler, M.: Algebraic connectivity of graphs. Czechoslov. Math. J. 23(2), 298–305 (1973)
Giles, C.L., Bollacker, K.D., Lawrence, S.: Citeseer: an automatic citation indexing system. In: Proceedings of the third ACM Conference on Digital Libraries, pp. 89–98 (1998)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Lin, L., Blaser, E., Wang, H.: Graph structural attack by perturbing spectral distance. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 989–998 (2022)
McCallum, A.K., Nigam, K., Rennie, J., Seymore, K.: Automating the construction of internet portals with machine learning. Inf. Retrieval 3(2), 127–163 (2000)
Milanović, J.V., Zhu, W.: Modeling of interconnected critical infrastructure systems using complex network theory. IEEE Trans. Smart Grid 9(5), 4637–4648 (2017)
Nar, K., Ocal, O., Sastry, S.S., Ramchandran, K.: Cross-entropy loss and low-rank features have responsibility for adversarial examples. arXiv preprint arXiv:1901.08360 (2019)
Nt, H., Maehara, T.: Revisiting graph neural networks: all we have is low-pass filters. arXiv preprint arXiv:1905.09550 (2019)
Oellermann, O.R., Schwenk, A.J.: The Laplacian spectrum of graphs. Graph Theory, c, Appl. 2, 871–898 (1991)
Qiu, J., Dong, Y., Ma, H., Li, J., Wang, K., Tang, J.: Network embedding as matrix factorization: unifying DeepWalk, LINE, PTE, and node2vec. In: Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, pp. 459–467 (2018)
Sen, P., Namata, G., Bilgic, M., Getoor, L., Galligher, B., Eliassi-Rad, T.: Collective classification in network data. AI Mag. 29(3), 93–93 (2008)
Stewart, G., Sun, J.: Matrix Perturbation Theory. Elsevier Science, Computer Science and Scientific Computing (1990)
Tong, H.E.A.: Gelling, and melting, large graphs by edge manipulation. In: Proceedings of 21st ACM International Conference on Information and Knowledge Management, pp. 245–254 (2012)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)
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)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, X., Ma, J., Dong, Y., Chen, C., Gao, M., Li, J. (2024). SD-Attack: Targeted Spectral Attacks on Graphs. In: Yang, DN., Xie, X., Tseng, V.S., Pei, J., Huang, JW., Lin, J.CW. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2024. Lecture Notes in Computer Science(), vol 14646. Springer, Singapore. https://doi.org/10.1007/978-981-97-2253-2_28
Download citation
DOI: https://doi.org/10.1007/978-981-97-2253-2_28
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2252-5
Online ISBN: 978-981-97-2253-2
eBook Packages: Computer ScienceComputer Science (R0)