Abstract
Data mining techniques allow us to discover patterns in large datasets. Nonetheless, data may contain sensitive information. This is especially true when data is georeferenced. Thus, an adversary could learn about individual whereabouts, points of interest, political affiliation, and even sexual habits. At the same time, human mobility is a rich source of information to analyze traffic jams, health care accessibility, food desserts, and even pandemics dynamics. Therefore, to enhance privacy, we study the use of Deep Learning techniques such as Generative Adversarial Network (GAN) and GAN with Differential Privacy (DP-GAN) to generate synthetic data with formal privacy guarantees. Our experiments demonstrate that we can generate synthetic data to maintain individuals’ privacy and data quality depending on privacy parameters. Accordingly, based on the privacy settings, we generated data differing a few meters and a few kilometers from the original trajectories. After generating fine-grain mobility trajectories at the GPS level through an adversarial neural networks approach and using GAN to sanitize the original trajectories together with differential privacy, we analyze the privacy provided from the perspective of anonymization literature. We show that such \(\epsilon \)-differentially private data may still have a risk of re-identification.
H. Alatrista-Salas, P. Montalvo-Garcia and M. Nunez-del-Prado—Contributed equally in the present work.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 214–223, 06–11 August 2017
Domingo-Ferrer, J., Sánchez, D., Blanco-Justicia, A.: The limits of differential privacy (and its misuse in data release and machine learning). Commun. ACM 64(7), 33–35 (2021). https://doi.org/10.1145/3433638
Dwork, C., Kenthapadi, K., McSherry, F., Mironov, I., Naor, M.: Our data, ourselves: privacy via distributed noise generation. In: Vaudenay, S. (ed.) EUROCRYPT 2006. LNCS, vol. 4004, pp. 486–503. Springer, Heidelberg (2006). https://doi.org/10.1007/11761679_29
Eigenschink, P., Vamosi, S., Vamosi, R., Sun, C., Reutterer, T., Kalcher, K.: Deep generative models for synthetic data. ACM Comput. Surv. (2021)
Fan, L.: A survey of differentially private generative adversarial networks. In: The AAAI Workshop on Privacy-Preserving Artificial Intelligence, p. 8 (2020)
Gambs, S., Killijian, M.O., Moise, I., del Prado Cortez, M.N.: MapReducing GEPETO or towards conducting a privacy analysis on millions of mobility traces. In: 2013 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum, pp. 1937–1946. IEEE (2013)
Gambs, S., Killijian, M.O., del Prado Cortez, M.N.: Show me how you move and i will tell you who you are. In: Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Security and Privacy in GIS and LBS, pp. 34–41 (2010)
Gambs, S., Killijian, M.O., del Prado Cortez, M.N.: Towards temporal mobility Markov chains. In: 1st International Workshop on Dynamicity Collocated with OPODIS 2011, Toulouse, France, pp. 2-pages (2011)
Gambs, S., Killijian, M.O., del Prado Cortez, M.N.: De-anonymization attack on geolocated data. J. Comput. Syst. Sci. 80(8), 1597–1614 (2014)
Golle, P., Partridge, K.: On the anonymity of home/work location pairs. In: Tokuda, H., Beigl, M., Friday, A., Brush, A.J.B., Tobe, Y. (eds.) Pervasive 2009. LNCS, vol. 5538, pp. 390–397. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-01516-8_26
Heinle, M.S., Smith, K.C.: A theory of risk disclosure. Rev. Acc. Stud. 22(4), 1459–1491 (2017). https://doi.org/10.1007/s11142-017-9414-2
Heredia-Ductram, D., Nunez-del Prado, M., Alatrista-Salas, H.: Toward a comparison of classical and new privacy mechanism. Entropy 23(4), 467 (2021)
Ho, S., Qu, Y., Gu, B., Gao, L., Li, J., Xiang, Y.: DP-GAN: differentially private consecutive data publishing using generative adversarial nets. J. Netw. Comput. Appl. 185, 103066 (2021)
Imtiaz, S., Arsalan, M., Vlassov, V., Sadre, R.: Synthetic and private smart health care data generation using GANs. In: 2021 International Conference on Computer Communications and Networks (ICCCN), pp. 1–7. IEEE (2021)
Kaiser, J., Bavendiek, K., Schupp, S.: Do we need real data? -Testing and training algorithms with artificial geolocation data. In: 50 Jahre Gesellschaft für Informatik, p. 205 (2019)
Liu, X., Chen, H., Andris, C.: trajGANs: using generative adversarial networks for geo-privacy protection of trajectory data (vision paper). In: Location Privacy and Security Workshop, pp. 1–7 (2018)
Ma, B., Yang, B., Zhang, Z., Zhang, J.: Modelling mobile traffic patterns using a generative adversarial neural networks. In: NOMS 2020–2020 IEEE/IFIP Network Operations and Management Symposium, pp. 1–7. IEEE (2020)
Nunez-del Prado, M., Nin, J.: Revisiting online anonymization algorithms to ensure location privacy. J. Ambient Intell. Human. Comput. 1–12 (2019). https://doi.org/10.1007/s12652-019-01371-6
Salas, J., Megías, D., Torra, V.: SwapMob: swapping trajectories for mobility anonymization. In: Domingo-Ferrer, J., Montes, F. (eds.) PSD 2018. LNCS, vol. 11126, pp. 331–346. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-99771-1_22
Song, H.Y., Baek, M.S., Sung, M.: Generating human mobility route based on generative adversarial network. In: 2019 Federated Conference on Computer Science and Information Systems (FedCSIS), pp. 91–99. IEEE (2019)
Xu, C., Ren, J., Zhang, D., Zhang, Y., Qin, Z., Ren, K.: GANobfuscator: mitigating information leakage under GAN via differential privacy. IEEE Trans. Inf. Forensics Secur. 14(9), 2358–2371 (2019)
Yin, D., Yang, Q.: GANs based density distribution privacy-preservation on mobility data. Secur. Commun. Netw. 2018 (2018)
Zang, H., Bolot, J.: Anonymization of location data does not work: a large-scale measurement study. In: Proceedings of the 17th Annual International Conference on Mobile Computing and Networking, pp. 145–156 (2011)
Zhan, Y., Kyllo, A., Mashhadi, A., Haddadi, H.: Privacy-aware human mobility prediction via adversarial networks. arXiv preprint arXiv:2201.07519 (2022)
Zhang, X., Ji, S., Wang, T.: Differentially private releasing via deep generative model (technical report). arXiv preprint arXiv:1801.01594 (2018)
Zheng, Y., Fu, H., Xie, X., Ma, W.Y., Li, Q.: Geolife GPS trajectory dataset-user guide. Geolife GPS trajectories 1, 2011 (2011)
Acknowledgements
This research was partly supported by the Spanish Government under project RTI2018-095094-B-C22 “CONSENT”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Alatrista-Salas, H., Montalvo-Garcia, P., Nunez-del-Prado, M., Salas, J. (2022). Geolocated Data Generation and Protection Using Generative Adversarial Networks. In: Torra, V., Narukawa, Y. (eds) Modeling Decisions for Artificial Intelligence. MDAI 2022. Lecture Notes in Computer Science(), vol 13408. Springer, Cham. https://doi.org/10.1007/978-3-031-13448-7_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-13448-7_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-13447-0
Online ISBN: 978-3-031-13448-7
eBook Packages: Computer ScienceComputer Science (R0)