Abstract
As social networks become indispensable for people’s daily lives, inference attacks pose significant threat to users’ privacy where attackers can infiltrate users’ information and infer their private attributes. In particular, social networks are represented as graph-structured data, maintaining rich user activities and complex relationships among them. This enables attackers to deploy state-of-the-art graph neural networks (GNNs) to automate attribute inference attacks for users’ privacy disclosure. To address this challenge, in this paper, we leverage the vulnerability of GNNs to adversarial attacks, and propose a new graph adversarial method, called Attribute-Obfuscating Attack (AttrOBF) to mislead GNNs into misclassification and thus protect user attribute privacy against GNN-based inference attacks on social networks. Different from the prior attacks using perturbations on graph structure or node features, AttrOBF provides a more practical formulation by obfuscating optimal training user attribute values, and also advances the attribute obfuscation by solving the unavailability issue of test attribute annotations, black-box setting, bi-level optimization, and non-differentiable obfuscating operation. We demonstrate the effectiveness of AttrOBF on user attribute obfuscation by extensive experiments over three real-world social network datasets. We believe our work yields great potential of applying adversarial attacks to attribute protection on social networks.
Keywords
- Attribute privacy
- Inference attack
- Social networks
- Graph adversarial attack
- Attribute obfuscation
X. Li and L. Chen—Equal contribution. Work done while at PSU.
This is a preview of subscription content, access via your institution.
Buying options
References
Abu-El-Haija, S., et al.: Mixhop: higher-order graph convolutional architectures via sparsified neighborhood mixing. In: International Conference on Machine Learning, pp. 21–29 (2019)
Adamic, L.A., Glance, N.: The political blogosphere and the 2004 us election: divided they blog. In: Proceedings of the 3rd International Workshop on Link Discovery, pp. 36–43 (2005)
Beigi, G., Shu, K., Zhang, Y., Liu, H.: Securing social media user data: an adversarial approach. In: Hypertext and Social Media, pp. 165–173 (2018)
Chen, J., Ma, T., Xiao, C.: FastGCN: fast learning with graph convolutional networks via importance sampling. arXiv preprint arXiv:1801.10247 (2018)
Chen, L., Li, X., Wu, D.: Enhancing robustness of graph convolutional networks via dropping graph connections. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 412–428 (2020)
Chen, L., Ye, Y., Bourlai, T.: Adversarial machine learning in malware detection: Arms race between evasion attack and defense. In: 2017 European Intelligence and Security Informatics Conference (EISIC), pp. 99–106. IEEE (2017)
Chen, W., et al.: Semi-supervised user profiling with heterogeneous graph attention networks. In: IJCAI, vol. 19, pp. 2116–2122 (2019)
Dai, H., et al.: Adversarial attack on graph structured data. arXiv preprint arXiv:1806.02371 (2018)
Gong, N.Z., Liu, B.: Attribute inference attacks in online social networks. TOPS 21(1), 3 (2018)
Hamilton, W.L., Ying, R., Leskovec, J.: Inductive representation learning on large graphs. arXiv preprint arXiv:1706.02216 (2017)
Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016)
Jia, J., Gong, N.Z.: AttriGuard: a practical defense against attribute inference attacks via adversarial machine learning. In: USENIX Security, pp. 513–529 (2018)
Jia, J., Wang, B., Zhang, L., Gong, N.Z.: Attriinfer: Inferring user attributes in online social networks using Markov random fields. In: WWW, pp. 1561–1569 (2017)
Jin, H., Zhang, X.: Robust training of graph convolutional networks via latent perturbation. In: Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2020, Ghent, Belgium, 14–18 September 2020, Proceedings, Part III, pp. 394–411 (2021)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Kumar, C., Ryan, R., Shao, M.: Adversary for social good: Protecting familial privacy through joint adversarial attacks. In: AAAI (2020)
Li, K., Luo, G., Ye, Y., Li, W., Ji, S., Cai, Z.: Adversarial privacy preserving graph embedding against inference attack. IEEE Internet Things J. 8(8), 6904–6915 (2020)
Li, X., Chen, L., Wu, D.: Turning attacks into protection: Social media privacy protection using adversarial attacks. In: Proceedings of the 2021 SIAM International Conference on Data Mining (SDM), pp. 208–216. SIAM (2021)
Liu, S., Chen, L., Dong, H., Wang, Z., Wu, D., Huang, Z.: Higher-order weighted graph convolutional networks. arXiv preprint arXiv:1911.04129 (2019)
Liu, X., Si, S., Zhu, X., Li, Y., Hsieh, C.J.: A unified framework for data poisoning attack to graph-based semi-supervised learning. arXiv:1910.14147 (2019)
Mohamed, A., Qian, K., Elhoseiny, M., Claudel, C.: Social-STGCNN: a social spatio-temporal graph convolutional neural network for human trajectory prediction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14424–14432 (2020)
Morgan-Lopez, A.A., Kim, A.E., Chew, R.F., Ruddle, P.: Predicting age groups of twitter users based on language and metadata features. PloS ONE 12(8), e0183537 (2017)
Oh, S.J., Fritz, M., Schiele, B.: Adversarial image perturbation for privacy protection a game theory perspective. In: ICCV, pp. 1491–1500 (2017)
Papernot, N., McDaniel, P., Goodfellow, I.: Transferability in machine learning: from phenomena to black-box attacks using adversarial samples. arXiv preprint arXiv:1605.07277 (2016)
Qian, J., Li, X.Y., Jung, T., Fan, Y., Wang, Y., Tang, S.: Social network de-anonymization: more adversarial knowledge, more users re-identified? TOIT 19(3), 1–22 (2019)
Ruder, S., Ghaffari, P., Breslin, J.G.: Character-level and multi-channel convolutional neural networks for large-scale authorship attribution. arXiv preprint arXiv:1609.06686 (2016)
Shetty, R., Schiele, B., Fritz, M.: A4nt: author attribute anonymity by adversarial training of neural machine translation. In: Proceedings of the 27th USENIX Security Symposium (USENIX Security 18), pp. 1633–1650 (2018)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)
Wang, H., Leskovec, J.: Unifying graph convolutional neural networks and label propagation. arXiv preprint arXiv:2002.06755 (2020)
Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., Weinberger, K.: Simplifying graph convolutional networks. In: International Conference on Machine Learning, pp. 6861–6871. PMLR (2019)
Wu, H., Wang, C., Tyshetskiy, Y., Docherty, A., Lu, K., Zhu, L.: Adversarial examples for graph data: deep insights into attack and defense. In: IJCAI, pp. 4816–4823 (2019)
Wu, Y., Lian, D., Jin, S., Chen, E.: Graph convolutional networks on user mobility heterogeneous graphs for social relationship inference. In: IJCAI, pp. 3898–3904 (2019)
Xu, K., et al.: Topology attack and defense for graph neural networks: an optimization perspective. arXiv preprint arXiv:1906.04214 (2019)
Ying, R., He, R., Chen, K., Eksombatchai, P., Hamilton, W.L., Leskovec, J.: Graph convolutional neural networks for web-scale recommender systems. In: SIGKDD, pp. 974–983 (2018)
Yu, S., Vorobeychik, Y., Alfeld, S.: Adversarial classification on social networks. In: AAMAS, pp. 211–219 (2018)
Zhang, M., Hu, L., Shi, C., Wang, X.: Adversarial label-flipping attack and defense for graph neural networks. In: ICDM, pp. 791–800 (2020)
Zhang, Y., Humbert, M., Rahman, T., Pang, J., Backes, M.: Tagvisor: a privacy advisor for sharing hashtags. In: WWW (2018)
Zügner, D., Akbarnejad, A., Günnemann, S.: Adversarial attacks on neural networks for graph data. In: SIGKDD, pp. 2847–2856 (2018)
Zügner, D., Günnemann, S.: Adversarial attacks on graph neural networks via meta learning. arXiv preprint arXiv:1902.08412 (2019)
Acknowledgement
The work was supported in part by a seed grant from the Penn State Center for Security Research and Education (CSRE).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Li, X., Chen, L., Wu, D. (2023). Adversary for Social Good: Leveraging Attribute-Obfuscating Attack to Protect User Privacy on Social Networks. In: Li, F., Liang, K., Lin, Z., Katsikas, S.K. (eds) Security and Privacy in Communication Networks. SecureComm 2022. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 462. Springer, Cham. https://doi.org/10.1007/978-3-031-25538-0_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-25538-0_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25537-3
Online ISBN: 978-3-031-25538-0
eBook Packages: Computer ScienceComputer Science (R0)