Abstract
Adversarial Machine Learning has emerged as a substantial subfield of Computer Science due to a lack of robustness in the models we train along with crowdsourcing practices that enable attackers to tamper with data. In the last two years, interest has surged in adversarial attacks on graphs yet the Graph Classification setting remains nearly untouched. Since a Graph Classification dataset consists of discrete graphs with class labels, related work has forgone direct gradient optimization in favor of an indirect Reinforcement Learning approach. We will study the novel problem of Data Poisoning (training-time) attacks on Neural Networks for Graph Classification using Reinforcement Learning Agents.
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
Jin, W., Li, Y., Xu, H., Wang, Y., Tang, J.: Adversarial attacks and defenses on graphs: a review and empirical study. arXiv preprint arXiv:2003.00653 (2020)
Xu, H., et al.: Adversarial attacks and defenses in images, graphs and text: a review. Int. J. Autom. Comput. 17, 151–178 (2020). https://doi.org/10.1007/s11633-019-1211-x
Goodfellow, I.J., et al.: Generative adversarial networks (2014)
Ren, K., Zheng, T., Qin, Z., Liu, X.: Adversarial attacks and defenses in deep learning. Engineering 6(3), 346–360 (2020)
Knyazev, B., Lin, X., Amer, M.R., Taylor, G.W.: Spectral multigraph networks for discovering and fusing relationships in molecules. arXiv:1811.09595 [cs, stat], November 2018
Ying, R., You, J., Morris, C., Ren, X., Hamilton, W.L., Leskovec, J.: Hierarchical graph representation learning with differentiable pooling. arXiv:1806.08804 [cs, stat], February 2019
Tramèr, F., Zhang, F., Juels, A., Reiter, M.K., Ristenpart, T.: Stealing machine learning models via prediction APIs. In: 25th USENIX Security Symposium (USENIX Security 2016), pp. 601–618 (2016)
Zhang, W.E., Sheng, Q.Z., Alhazmi, A., Li, C.: Adversarial attacks on deep-learning models in natural language processing: a survey. ACM Trans. Intell. Syst. Technol. 11(3) (2020). https://doi.org/10.1145/3374217
Tixier, A.J.-P., Nikolentzos, G., Meladianos, P., Vazirgiannis, M.: Graph classification with 2D convolutional neural networks. In: Tetko, I.V., Kůrková, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11731, pp. 578–593. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30493-5_54
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Dai, H., et al.: Adversarial attack on graph structured data. arXiv:1806.02371 [cs, stat], June 2018
Ma, Y., Wang, S., Derr, T., Wu, L., Tang, J.: Attacking graph convolutional networks via rewiring. arXiv:1906.03750 [cs, stat], September 2019
Zhang, Z., Jia, J., Wang, B., Gong, N.Z.: Backdoor attacks to graph neural networks. arXiv:2006.11165 [cs], June 2020
Papernot, N., McDaniel, P., Swami, A., Harang, R.: Crafting adversarial input sequences for recurrent neural networks (2016)
Akhtar, N., Mian, A.: Threat of adversarial attacks on deep learning in computer vision: a survey. arXiv:1801.00553 [cs], February 2018
Xu, X., Yu, Y., Li, B., Song, L., Liu, C., Gunter, C.: Characterizing malicious edges targeting on graph neural networks (2019). https://openreview.net/forum?id=HJxdAoCcYX
Zhu, D., Zhang, Z., Cui, P., Zhu, W.: Robust graph convolutional networks against adversarial attacks. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2019, pp. 1399–1407. Association for Computing Machinery, New York (2019). https://doi.org/10.1145/3292500.3330851
Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? arXiv:1810.00826 [cs, stat], February 2019
Wang, M., et al.: Deep graph library: a graph-centric, highly-performant package for graph neural networks. arXiv preprint arXiv:1909.01315 (2019)
Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3), 229–256 (1992). https://doi.org/10.1007/BF00992696
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Dineen, J., Haque, A.S.M.AU., Bielskas, M. (2021). Reinforcement Learning for Data Poisoning on Graph Neural Networks. In: Thomson, R., Hussain, M.N., Dancy, C., Pyke, A. (eds) Social, Cultural, and Behavioral Modeling. SBP-BRiMS 2021. Lecture Notes in Computer Science(), vol 12720. Springer, Cham. https://doi.org/10.1007/978-3-030-80387-2_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-80387-2_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-80386-5
Online ISBN: 978-3-030-80387-2
eBook Packages: Computer ScienceComputer Science (R0)