Journal of Soft Computing Paradigm
IRO Journals
Volume 7 — Issue 3 — September 2025

Differentially Private Time Series Wasserstein Generative Adversarial Network for Private and Utilizable Synthetic Time Series Data Generation

https://doi.org/10.36548/jscp.2025.3.002
Sathiyapriya K.
Department of Computer Science and Engineering, PSG College of Technology, Coimbatore, India
Mridula M.
Department of Computer Science and Engineering, PSG College of Technology, Coimbatore, India
Kumaresh S.
Department of Computer Science and Engineering, PSG College of Technology, Coimbatore, India
Sravya Vankadara
Department of Computer Science and Engineering, PSG College of Technology, Coimbatore, India
PDF
PDF

How to Cite

K., Sathiyapriya, Mridula M., Kumaresh S., and Sravya Vankadara. 2025. “Differentially Private Time Series Wasserstein Generative Adversarial Network for Private and Utilizable Synthetic Time Series Data Generation”. Journal of Soft Computing Paradigm 7 (3): 212-36. https://doi.org/10.36548/jscp.2025.3.002.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

— Generative Adversarial Networks
— Synthetic Data
— Differential Privacy
— Privacy-Utility Trade-Off
— Time-Series Data
— Tabular Data
— Wasserstein Distance
Published: 12-08-2025

Abstract

The humongous volumes of data utilized to train the machine learning models are vulnerable to leakage by model inversion attacks and membership inference attacks. These days, massive amounts of research are being conducted to leverage differential privacy to safeguard the privacy of users. Tabular data generation from differentially private generative adversarial networks is still an untapped area. This work suggests a framework to enhance privacy protection in generating synthetic data by utilizing Wasserstein distance. The developed architecture generated synthetic data that replicated the time series relations of real-world data without compromising identifiable features of members of the input data. Results obtained from the architecture were compared with two other current GAN frameworks, DP-WGAN, and Time GAN. The privacy vs. utility tradeoff was found to be improved in the case of the architecture under discussion, as can be seen from the RMSE scores and Overall Quality Report.

References

  1. Madhu, M., and P. Whig. "A survey of machine learning and its applications." International Journal of Machine Learning for Sustainable Development 4, no. 1 (2022): 11-20.
  2. Kapoor, Sayash, and Arvind Narayanan. "Leakage and the reproducibility crisis in ML-based science." arXiv preprint arXiv:2207.07048 (2022).
  3. Liu, Ximeng, Lehui Xie, Yaopeng Wang, Jian Zou, Jinbo Xiong, Zuobin Ying, and Athanasios V. Vasilakos. "Privacy and security issues in deep learning: A survey." IEEe Access 9 (2020): 4566-4593.
  4. Sun, Hui, Tianqing Zhu, Zhiqiu Zhang, Dawei Jin, Ping Xiong, and Wanlei Zhou. "Adversarial attacks against deep generative models on data: A survey." IEEE Transactions on Knowledge and Data Engineering 35, no. 4 (2021): 3367-3388.
  5. Zhang, Yuheng, Ruoxi Jia, Hengzhi Pei, Wenxiao Wang, Bo Li, and Dawn Song. "The secret revealer: Generative model-inversion attacks against deep neural networks." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, (2020): 253-261.
  6. Gupta, Rajesh, Sudeep Tanwar, Sudhanshu Tyagi, and Neeraj Kumar. "Machine learning models for secure data analytics: A taxonomy and threat model." Computer Communications 153 (2020): 406-440.
  7. Ghatak, Debolina, and Kouichi Sakurai. "A survey on privacy preserving synthetic data generation and a discussion on a privacy-utility trade-off problem." In International Conference on Science of Cyber Security, Singapore: Springer Nature Singapore, (2022): 167-180.
  8. Abadi, Martin, Andy Chu, Ian Goodfellow, H. Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang. "Deep learning with differential privacy." In Proceedings of the 2016 ACM SIGSAC conference on computer and communications security, (2016): 308-318.
  9. Ha, Trung, Tran Khanh Dang, Tran Tri Dang, Tuan Anh Truong, and Manh Tuan Nguyen. "Differential privacy in deep learning: an overview." In 2019 International Conference on Advanced Computing and Applications (ACOMP), IEEE, (2019): 97-102.
  10. Mirza, Mehdi, and Simon Osindero. "Conditional generative adversarial nets." arXiv preprint arXiv:1411.1784 (2014).
  11. Arjovsky, Martin, Soumith Chintala, and Léon Bottou. "Wasserstein generative adversarial networks." In International conference on machine learning, PMLR, (2017): 214-223.
  12. Jordon, James, Jinsung Yoon, and Mihaela Van Der Schaar. "PATE-GAN: Generating synthetic data with differential privacy guarantees." In International conference on learning representations. 2018.
  13. TeMarvelde, Pepijn. "Differentially Private GAN for Time Series." CSE3000 research project, Delft University of Technology, http://resolver.tudelft.nl/uuid:8c4171d0-db68-4235-badb-6e57953162b8 (2021).
  14. Analytics, Data, and Valtteri Nieminen. "Differentially private synthetic tabular data generation with a generative adversarial network and privacy amplification by subsampling." (2022).
  15. Song, Shuang, Kamalika Chaudhuri, and Anand D. Sarwate. "Stochastic gradient descent with differentially private updates." In 2013 IEEE global conference on signal and information processing, IEEE, (2013): 245-248.
  16. Ghosheh, Ghadeer, Jin Li, and Tingting Zhu. "A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sources." arXiv preprint arXiv:2203.07018 (2022).
  17. L. Xie, K. Lin, S. Wang, F. Wang, and J. Zhou, "Differentially Private Generative Adversarial Network with Representation Learning," IEEE Transactions on Knowledge and Data Engineering, vol. 33, no. 11, Nov. (2021): 3784–3797. doi: 10.1109/TKDE.2020.2981333.
  18. R. Chen, M. Yu, M. Zhang, L. Yu, and L. Fan, "PrivSyn: Differentially Private Data Synthesis via Generative Adversarial Networks," in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 7, (2023): 7542–7550. doi: 10.1609/aaai.v37i7.25973.
  19. C. Esteban, S. L. Hyland, and G. Rätsch, "Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs," in Proceedings of the Machine Learning for Healthcare Conference (MLHC), PMLR 149: (2022): 325–350.
  20. R. Torkzadehmahani, P. Kairouz, and B. Paten, "DP-CGAN: Differentially Private Synthetic Data and Label Generation," IEEE Transactions on Dependable and Secure Computing, vol. 20, no. 1, Jan.–Feb. (2023): 190–204. doi: 10.1109/TDSC.2021.3119550.
  21. B. Zhang, J. Sun, J. Zhao, and Y. Zhu, "Towards Privacy-Preserving Time-Series Generation via Dual-Stage GANs," arXiv preprint arXiv:2209.09977, 2022.[Online]. Available: https://arxiv.org/abs/2209.09977
  22. A. Mohamed, U. Thakker, and B. Li, "SecureGAN: Scalable Differentially Private GANs for High-Dimensional Data," in NeurIPS 2023 Workshop on Synthetic Data Generation, New Orleans, LA, USA, 2023. Available: https://openreview.net/forum?id=secgan23