Privacy-Preserving k-NN Graphs with Autoencoder-Based Representations for Sensitive Features

• Gustavo Lima de Oliveira USP
• Maria da Graça Campos Pimentel USP
• Ricardo M. Marcacini USP

DOI: https://doi.org/10.5753/eniac.2024.245212

Resumo

Privacy-preserving representation learning has gained significant attention for enabling secure data and model sharing by protecting sensitive information while maintaining data utility. In this paper, we present a new approach to privacy-preserving representation learning with k-NN-based graph models. This method maps the original feature space to a new space that balances feature utility, such as classification accuracy, with reducing privacy attack risks, and constructs a kNN graph from this new space. We evaluate three scenarios using real datasets to assess privacy-preserving graph representations. Experimental results show that learning a privacy-preserved representation and constructing a k-NN graph is a simple, intuitive, and competitive approach compared to other methods in the literature. Thus, this method enables graph data sharing with a lower risk of sensitive information extraction attacks.

Palavras-chave: Privacy-Preserving, Graph, Autoencoder

Referências

Al-Rubaie, M. and Chang, J. M. (2019). Privacy-preserving machine learning: Threats and solutions. IEEE Security & Privacy, 17(2):49–58.

Backstrom, L., Dwork, C., and Kleinberg, J. (2007). Wherefore art thou r3579x? anonymized social networks, hidden patterns, and structural steganography. In Proceedings of the 16th International Conference on World Wide Web, WWW ’07, page 181–190, New York, NY, USA. Association for Computing Machinery.

Chen, H., Zhu, T., Zhang, T., Zhou, W., and Yu, P. S. (2023). Privacy and fairness in federated learning: perspective of tradeoff. ACM Computing Surveys, 56(2):1–37.

Fu, D., Bao, W., Maciejewski, R., Tong, H., and He, J. (2023). Privacy-preserving graph machine learning from data to computation: A survey. SIGKDD Explor. Newsl., 25(1):54–72.

Han, X., Yang, Y., Wang, L., and Wu, J. (2023). Privacy-preserving network embedding against private link inference attacks. IEEE Transactions on Dependable and Secure Computing.

Hay, M., Miklau, G., Jensen, D., Towsley, D., and Weis, P. (2008). Resisting structural re-identification in anonymized social networks. Proc. VLDB Endow., 1(1):102–114.

Hoang, V. T., Jeon, H.-J., You, E.-S., Yoon, Y., Jung, S., and Lee, O.-J. (2023). Graph representation learning and its applications: a survey. Sensors, 23(8):4168.

Kong, C., Chen, B., Li, S., Chen, Y., Chen, J., Zhou, Q., Wang, D., and Zhang, L. (2020). Privacy attack and defense in network embedding. In International Conference on Computational Data and Social Networks, pages 231–242. Springer.

Li, K., Luo, G., Ye, Y., Li, W., Ji, S., and Cai, Z. (2020a). Adversarial privacy-preserving graph embedding against inference attack. IEEE Internet of Things Journal, 8(8):6904–6915.

Li, L., Fan, Y., Tse, M., and Lin, K.-Y. (2020b). A review of applications in federated learning. Computers Industrial Engineering, 149:106854.

Liu, K. and Terzi, E. (2008). Towards identity anonymization on graphs. In Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, SIGMOD ’08, page 93–106, New York, NY, USA. Association for Computing Machinery.

Ma, L., Li, C., Sun, S., Guo, S., Wang, L., and Li, J. (2024). Privacy-preserving graph publishing with disentangled variational information bottleneck. Concurrency and Computation: Practice and Experience, 36(10):e7963.

Nasr, M., Mahloujifar, S., Tang, X., Mittal, P., and Houmansadr, A. (2023). Effectively using public data in privacy preserving machine learning. In International Conference on Machine Learning, pages 25718–25732. PMLR.

Oliveira, G. L., Marcacini, R. M., and Pimentel, M. d. G. C. (2021). Privacy-preserving on heterogeneous network embedding for clinical events. Proceedings of the First MLSys Workshop on Graph Neural Net-works and Systems (GNNSys’21).

Tran, A.-T., Luong, T.-D., and Huynh, V.-N. (2024). A comprehensive survey and taxonomy on privacy-preserving deep learning. Neurocomputing, page 127345.