Abstract
As the number of graph-level embedding techniques increases at an unprecedented speed, questions arise about their behavior and performance when training data undergo perturbations. This is the case when an external entity maliciously alters training data to invalidate the embedding. This paper explores the effects of such attacks on some graph datasets by applying different graph-level embedding techniques. The main attack strategy involves manipulating training data to produce an altered model. In this context, our goal is to go in-depth about methods, resources, experimental settings, and performance results to observe and study all the aspects that derive from the attack stage.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
Data availability
Data and algorithms used in the current work are all available as open source.
Code availability
The software used in the current experimental study is publicly available for reproducibility of results.
Notes
available at https://github.com/cds-group/Netpro2vec
available at https://karateclub.readthedocs.io
References
Vlietstra, W.J., Vos, R., Sijbers, A.M., van Mulligen, E.M., Kors, J.A.: Using predicate and provenance information from a knowledge graph for drug efficacy screening. J. Biomed. Semantics 9(1), 1–10 (2018)
Manipur, I., Granata, I., Maddalena, L., Guarracino, M.R.: Clustering analysis of tumor metabolic networks. BMC Bioinformatics 21(10), 349 (2020). https://doi.org/10.1186/s12859-020-03564-9
Thorne, T., Stumpf, M.P.: Graph spectral analysis of protein interaction network evolution. J. R. Soc. Interface. 9(75), 2653–2666 (2012)
Ding, S., Chen, C., Zhang, Q., Xin, B., Pardalos, P.M.: Metaheuristics for Resource Deployment Under Uncertainty in Complex Systems. CRC Press, (2021)
Chen, C., Wu, X., Chen, J., et al.: Dynamic grouping of heterogeneous agents for exploration and strike missions. Front. Inform. Technol. Electron. Eng. 23, 86–100 (2022). https://doi.org/10.1631/FITEE.2000352
Lin, Y., Liu, Z., Sun, M., Liu, Y., Zhu, X.: Learning entity and relation embeddings for knowledge graph completion. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 29 (2015)
Cai, H., Zheng, V.W., Chang, K.: A comprehensive survey of graph embedding: Problems, techniques, and applications. IEEE Trans. Knowl. Data Eng. 30(09), 1616–1637 (2018). https://doi.org/10.1109/TKDE.2018.2807452
Goyal, P., Ferrara, E.: Graph embedding techniques, applications, and performance: A survey. Knowl.-Based Syst. 151, 78–94 (2018). https://doi.org/10.1016/j.knosys.2018.03.022
Maddalena, L., Manipur, I., Manzo, M., Guarracino, M.R.: On whole-graph embedding techniques. In: Mondaini, R.P. (ed.) Trends in Biomathematics: Chaos and Control in Epidemics, Ecosystems, and Cells: Selected Works from the 20th BIOMAT Consortium Lectures, Rio de Janeiro, Brazil, 2020, pp. 115–131. Springer, (2021). https://doi.org/10.1007/978-3-030-73241-7_8
Huang, L., Joseph, A.D., Nelson, B., Rubinstein, B.I.P., Tygar, J.D.: Adversarial machine learning. In: Proceedings of the 4th ACM Workshop on Security and Artificial Intelligence. AISec ’11, pp. 43–58. Association for Computing Machinery, (2011). https://doi.org/10.1145/2046684.2046692
Akhtar, N., Mian, A.: Threat of adversarial attacks on deep learning in computer vision: A survey. IEEE Access 6, 14410–14430 (2018). https://doi.org/10.1109/ACCESS.2018.2807385
Qiu, S., Liu, Q., Zhou, S., Wu, C.: Review of artificial intelligence adversarial attack and defense technologies. Appl. Sci.9(5) (2019). https://doi.org/10.3390/app9050909
Gao, J., Lanchantin, J., Soffa, M.L., Qi, Y.: Black-box generation of adversarial text sequences to evade deep learning classifiers. In: 2018 IEEE Security and Privacy Workshops (SPW), pp. 50–56 (2018). https://doi.org/10.1109/SPW.2018.00016
Rosenberg, I., Shabtai, A., Rokach, L., Elovici, Y.: Generic black-box end-to-end attack against state of the art api call based malware classifiers. In: Bailey, M., Holz, T., Stamatogiannakis, M., Ioannidis, S. (eds.) Research in Attacks, Intrusions, and Defenses, pp. 490–510. Springer, (2018)
Jin, W., Li, Y., Xu, H., Wang, Y., Ji, S., Aggarwal, C., Tang, J.: Adversarial attacks and defenses on graphs. SIGKDD Explor. Newsl. 22(2), 19–34 (2021). https://doi.org/10.1145/3447556.3447566
Chen, L., Li, J., Peng, J., Xie, T., Cao, Z., Xu, K., He, X., Zheng, Z.: A survey of adversarial learning on graphs. (2020). arXiv:2003.05730. Accessed 29 Sept 2022
Sun, L., Wang, J., Yu, P.S., Li, B.: Adversarial attack and defense on graph data: A survey.(2020). arXiv:1812.10528. Accessed 29 Sept 2022
Chen, L., Wang, S., Yan, X.: Centroid-based clustering for graph datasets. In: Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), pp. 2144–2147 (2012)
Xi, Z., Pang, R., Ji, S., Wang, T.: Graph backdoor. In: 30th USENIX Security Symposium (USENIX Security 21) (2021)
Zhang, Z., Jia, J., Wang, B., Gong, N.Z.: Backdoor attacks to graph neural networks. In: Proceedings of the 26th ACM Symposium on Access Control Models and Technologies, pp. 15–26 (2021)
Manzo, M., Giordano, M., Maddalena, L., Guarracino, M.R.: Performance evaluation of adversarial attacks on whole-graph embedding models. In: Simos, D.E., Pardalos, P.M., Kotsireas, I.S.K. (eds.) Learning and Intelligent Optimization. LNCS. Springer, (2021)
Maddalena, L., Giordano, M., Manzo, M., Guarracino, M.R.: Whole-graph embedding and adversarial attacks for life sciences. In: Mondaini, R.P. (ed.) Trends in Biomathematics: Chaos and Control in Epidemics, Ecosystems, and Cells: Selected Works from the 21st BIOMAT Consortium Lectures, 2021. Springer, (2022)
Debnath, A., Lopez de Compadre, R., Debnath, G., Shusterman, A., Hansch, C.: Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. correlation with molecular orbital energies and hydrophobicity. J. Med. Chem. (34) (1991). https://doi.org/10.1021/jm00106a046
Borgwardt, K.M., Kriegel, H.P.: Shortest-path kernels on graphs. In: Fifth IEEE International Conference on Data Mining (ICDM’05), p. 8 (2005). https://doi.org/10.1109/ICDM.2005.132
Granata, I., Guarracino, M.R., Kalyagin, V.A., Maddalena, L., Manipur, I., Pardalos, P.M.: Supervised classification of metabolic networks. In: 2018 IEEE Int. Conf. on Bioinformatics and Biomedicine (BIBM), pp. 2688–2693. IEEE (2018)
Granata, I., Guarracino, M.R., Kalyagin, V.A., Maddalena, L., Manipur, I., Pardalos, P.M.: Model simplification for supervised classification of metabolic networks. Ann. Math. Artif. Intell. 88(1), 91–104 (2020)
Manipur, I., Granata, I., Maddalena, L., Guarracino, M.R.: Clustering analysis of tumor metabolic networks. BMC Bioinformatics (2020). https://doi.org/10.1186/s12859-020-03564-9
Uhlén, M., Fagerberg, L., Hallström, B.M., Lindskog, C., Oksvold, P., Mardinoglu, A., Sivertsson, Å, Kampf, C., Sjöstedt, E., Asplund, A., et al.: Tissue-based map of the human proteome. Science 347(6220) (2015)
Brandes, U.: On variants of shortest-path betweenness centrality and their generic computation. Social Networks 30(2), 136–145 (2008). https://doi.org/10.1016/j.socnet.2007.11.001
Bonacich, P.: Power and centrality: A family of measures. Am. J. Sociol. 92(5), 1170–1182 (1987). Accessed 2022 June 01
Page, L., Brin, S., Motwani, R., Winograd, T.: The pagerank citation ranking: Bringing order to the web. Technical Report 1999-66, Stanford InfoLab. Previous number = SIDL-WP-1999-0120. (1999). http://ilpubs.stanford.edu:8090/422/
Manipur, I., Manzo, M., Granata, I., Giordano, M., Maddalena, L., Guarracino, M.: Netpro2vec: a graph embedding framework for biomedical applications. IEEE/ACM Trans. Comput. Biol. Bioinform. 1–1 (2021). https://doi.org/10.1109/TCBB.2021.3078089
Narayanan, A., Chandramohan, M., Venkatesan, R., Chen, L., Liu, Y., Jaiswal, S.: graph2vec: Learning distributed representations of graphs. (2017). arXiv:1707.05005
Rozemberczki, B., Sarkar, R.: Characteristic functions on graphs: Birds of a feather, from statistical descriptors to parametric models. In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management. CIKM ’20, pp. 1325–1334. Association for Computing Machinery, (2020). https://doi.org/10.1145/3340531.3411866
Mikolov, T., Le, Q.V., Sutskever, I.: Exploiting similarities among languages for machine translation. (2013). arXiv:1309.4168. Accessed 29 Sept 2022
Le, Q., Mikolov, T.: Distributed representations of sentences and documents. In: Xing, E.P., Jebara, T. (eds.) Proceedings of the 31st International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 32, pp. 1188–1196. PMLR, (2014). https://proceedings.mlr.press/v32/le14.html. Accessed 29 Sept 2022
Matthews, B.W.: Comparison of the predicted and observed secondary structure of t4 phage lysozyme. Biochimica et Biophysica Acta (BBA) - Protein Structure 405(2), 442–451 (1975). https://doi.org/10.1016/0005-2795(75)90109-9
Acknowledgements
Mario Manzo thanks Prof. Alfredo Petrosino for the guidance and supervision during the years of working together.
Funding
This work has been partially funded by the BiBiNet project (H35F21000430002) within POR-Lazio FESR 2014-2020. It was carried out also within the activities of the authors as members of the ICAR-CNR INdAM Research Unit and partially supported by the INdAM research project “Computational Intelligence methods for Digital Health”. The work of Mario R. Guarracino was conducted within the framework of the Basic Research Program at the National Research University Higher School of Economics (HSE).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethics approval and consent to participate
Datasets used in the current work are all from secondary sources, where primary ethics approval had been obtained for data acquisition.
Consent for publication
Not applicable.
Conflicts of interest
The authors declare that they have no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix A: Performance measures of graph-embedding methods
In this appendix, we include tables reporting measures of 10-fold classification accuracy (acc), precision (prec), F-measure (f1), recall, and Matthews Correlation Coefficients (MCC) obtained in all the experiments. One table is reported for each experiment bunch, referring to the classification performance of one graph-embedding method (iNetpro2vec, iGraph2Vec, or FEATHER) when applied to one dataset (MUTAG, PROTEINS, or Kidney). In each table, we report the performance results when the dataset is unattacked (first row) and in the case of different percentages of edge removal (budget). The rows are grouped according to the criterion adopted for edge removal (random, betweenness, eigenvector, or pagerank) (Tables 3, 4, 5, 6, 7, 8, 9, 10 and 11).
Appedix B: Parameter settings of graph-embedding methods
Table 12 reports the parameter settings for the software implementations of Netpro2vec,Footnote 1 Graph2Vec,Footnote 2 and FEATHER2 adopted in the experiments. These parameters have been experimentally chosen to optimize MCC performance.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Giordano, M., Maddalena, L., Manzo, M. et al. Adversarial attacks on graph-level embedding methods: a case study. Ann Math Artif Intell 91, 259–285 (2023). https://doi.org/10.1007/s10472-022-09811-4
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10472-022-09811-4
Keywords
- Adversarial attacks
- Adversarial machine learning
- Graph embedding
- Graph neural networks
- Graph classification