AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
View PDF
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Open Access

Link-Privacy Preserving Graph Embedding Data Publication with Adversarial Learning

Department of Computer Science, Georgia State University, Atlanta, GA 30303, USA
Department of Electrical and Computer Engineering, George Mason University, Fairfax, VA 22030, USA
National Center of Excellence in Software, Sangmyung University, Seoul 03016, Republic of Korea
Show Author Information

Abstract

The inefficient utilization of ubiquitous graph data with combinatorial structures necessitates graph embedding methods, aiming at learning a continuous vector space for the graph, which is amenable to be adopted in traditional machine learning algorithms in favor of vector representations. Graph embedding methods build an important bridge between social network analysis and data analytics, as social networks naturally generate an unprecedented volume of graph data continuously. Publishing social network data not only brings benefit for public health, disaster response, commercial promotion, and many other applications, but also gives birth to threats that jeopardize each individual’s privacy and security. Unfortunately, most existing works in publishing social graph embedding data only focus on preserving social graph structure with less attention paid to the privacy issues inherited from social networks. To be specific, attackers can infer the presence of a sensitive relationship between two individuals by training a predictive model with the exposed social network embedding. In this paper, we propose a novel link-privacy preserved graph embedding framework using adversarial learning, which can reduce adversary’s prediction accuracy on sensitive links, while persevering sufficient non-sensitive information, such as graph topology and node attributes in graph embedding. Extensive experiments are conducted to evaluate the proposed framework using ground truth social network datasets.

References

[1]
J. S. He, M. Han, S. Ji, T. Du, and Z. Li, Spreading social influence with both positive and negative opinions in online networks, Big Data Mining and Analytics, vol. 2, no. 2, pp. 100-117, 2019.
[2]
X. Zheng, G. C. Luo, and Z. P. Cai, A fair mechanism for private data publication in online social networks, IEEE Transactions on Network Science and Engineering, vol. 7, no. 2, pp. 880-891, 2020.
[3]
M. Siddula, Y. S. Li, X. Z. Cheng, Z. Tian, and Z. P. Cai, Anonymization in online social networks based on enhanced Equi-Cardinal clustering, IEEE Transactions on Computational Social Systems, vol. 6, no. 4, pp. 809-820, 2019.
[4]
X. Zheng, Z. P. Cai, G. C. Luo, L. Tian, and X. Bai, Privacy-preserved community discovery in online social networks, Future Generation Computer Systems, vol. 93, pp. 1002-1009, 2019.
[5]
X. Zheng, Z. P. Cai, J. G. Yu, C. K. Wang, and Y. S. Li, Follow but no track: Privacy preserved profile publishing in cyber-physical social systems, IEEE Internet of Things Journal, vol. 4, no. 6, pp. 1868-1878, 2017.
[6]
P. Goyal and E. Ferrara, Graph embedding techniques, applications, and performance: A survey, Knowledge-Based Systems, vol. 151, pp. 78-94, 2018.
[7]
Z. B. He, Z. P. Cai, and J. G. Yu, Latent-data privacy preserving with customized data utility for social network data, IEEE Transactions on Vehicular Technology, vol. 67, no. 1, pp. 665-673, 2018.
[8]
M. Ellers, M. Cochez, T. Schumacher, M. Strohmaier, and F. Lemmerich, Privacy attacks on network embeddings, arXiv preprint arXiv: 1912.10979, 2019.
[9]
P. Drake, Who owns celebrity? Privacy, publicity and the legal regulation of celebrity images, in Stardom and Celebrity: A Reader, S. Redmond, and S. Holmes, eds. London, UK: SAGE Publications Ltd., 2007, pp. 219-229.
[10]
P. Cockerton, David Beckham and Prince William pictured together for campaign against ivory and rhino horn, https://www.mirror.co.uk/news/uk-news/david-beckham-prince-william-pictured-2272167, 2013.
[11]
B. Perozzi, R. Al-Rfou, and S. Skiena, DeepWalk: Online learning of social representations, in Proc. 20th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, New York, NY, USA, 2014, pp. 701-710.
[12]
T. Mikolov, K. Chen, G. Corrado, and J. Dean, Efficient estimation of word representations in vector space, arXiv preprint arXiv: 1301.3781, 2013.
[13]
A. Grover and J. Leskovec, node2vec: Scalable feature learning for networks, in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016, pp. 855-864.
[14]
J. Tang, M. Qu, M. Z. Wang, M. Zhang, J. Yan, and Q. Z. Mei, LINE: Large-scale information network embedding, in Proc. 24th Int. Conf. World Wide Web, Florence, Italy, 2015, pp. 1067-1077.
[15]
D. X. Wang, P. Cui, and W. W. Zhu, Structural deep network embedding, in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016, pp. 1225-1234.
[16]
T. N. Kipf and M. Welling, Variational graph auto-encoders, arXiv preprint arXiv: 1611.07308, 2016.
[17]
R. van den Berg, T. N. Kipf, and M. Welling, Graph convolutional matrix completion, arXiv preprint arXiv: 1706.02263, 2017.
[18]
K. Yang, J. Zhu, and X. Guo, POI neural-rec model via graph embedding representation, Tsinghua Science and Technology, vol. 26, no. 2, pp. 208-218, 2021.
[19]
A. Korolova, R. Motwani, S. U. Nabar, and Y. Xu, Link privacy in social networks, in Proc. 17th ACM Conf. Information and Knowledge Management, Napa Valley, CA, USA, 2008, pp. 289-298.
[20]
X. W. Ying and X. T. Wu, On link privacy in randomizing social networks, in Pacific-Asia Conference on Knowledge Discovery and Data Mining. Bangkok, Thailand: Springer, 2009, pp. 28-39.
[21]
M. Fire, G. Katz, L. Rokach, and Y. Elovici, Links reconstruction attack, in Security and Privacy in Social Networks. New York, NY, USA: Springer, 2013, pp. 181-196.
[22]
A. M. Fard and K. Wang, Neighborhood randomization for link privacy in social network analysis, World Wide Web, vol. 18, no. 1, pp. 9-32, 2015.
[23]
Z. P. Cai, Z. B. He, X. Guan, and Y. S. Li, Collective data-sanitization for preventing sensitive information inference attacks in social networks, IEEE Transactions on Dependable and Secure Computing, vol. 15, no. 4, pp. 577-590, 2018.
[24]
D. P. Xu, S. H. Yuan, X. T. Wu, and H. Phan, DPNE: Differentially private network embedding, in Pacific-Asia Conference on Knowledge Discovery and Data Mining. Melbourne, Australia: Springer, 2018, pp. 235-246.
[25]
S. Zhang and W. W. Ni, Graph embedding matrix sharing with differential privacy, IEEE Access, vol. 7, pp. 89390-89399, 2019.
[26]
A. Makhzani, J. Shlens, N. Jaitly, and I. Goodfellow, Adversarial autoencoders, arXiv preprint arXiv: 1511.05644, 2015.
[27]
K. Y. Li, G. C. Luo, Y. Ye, W. Li, S. H. Ji, and Z. P. Cai, Adversarial privacy preserving graph embedding against inference attack, IEEE Internet of Things Journal, .
[28]
A. Pareja, G. Domeniconi, J. Chen, T. F. Ma, T. Suzumura, H. Kanezashi, T. Kaler, T. Schardl, and C. Leiserson, EvolveGCN: Evolving graph convolutional networks for dynamic graphs, Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 4, pp. 5363-5370, 2020.
Tsinghua Science and Technology
Pages 244-256
Cite this article:
Zhang K, Tian Z, Cai Z, et al. Link-Privacy Preserving Graph Embedding Data Publication with Adversarial Learning. Tsinghua Science and Technology, 2022, 27(2): 244-256. https://doi.org/10.26599/TST.2021.9010015

810

Views

84

Downloads

18

Crossref

16

Web of Science

20

Scopus

0

CSCD

Altmetrics

Received: 26 December 2020
Revised: 07 February 2021
Accepted: 23 February 2021
Published: 29 September 2021
© The author(s) 2022

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).

Return