EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Privacy-Preserving GAN for Synthetic Data against Membership Inference Attack

Guizhang Cui, Guowei Wu, Lin Yao, Haibo Hu

ACM Transactions on Privacy and Security · 31.08.2026 · 29 (3) · 1-23

DOI: 10.1145/3820889 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Privacy and Security, online erschienen am 05.08.2026. Verfasst von Guizhang Cui und 3 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-quality data are essential for machine learning and data-driven research, yet data scarcity and privacy concerns remain major obstacles in many domains. Generative models have recently emerged as a promising approach to synthesize data that follow the same statistical distribution as real datasets. However, generative models are vulnerable to membership inference attacks, which threaten data confidentiality by exploiting model outputs to infer whether specific samples were used in training. Existing defense strategies struggle to simultaneously preserve data utility and provide robust privacy protection. To address this challenge, we propose our PPGM-GAN, a Privacy-Preserving GAN for synthetic data against membership inference attack to balance both data utility and data privacy. PPGM-GAN balances privacy and utility through a privacy-utility tradeoff function that quantifies and optimizes both aspects under different adversarial knowledge. To enhance data utility, we incorporate conditional generation and key-attribute screening to ensure sufficient representation of infrequent attribute values. Additionally, differential privacy is employed during training to prevent overfitting and reduce privacy leakage. Experimental results demonstrate that PPGM-GAN outperforms state-of-the-art privacy-preserving generative models, producing high-utility synthetic data under the same privacy constraints.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Cui, G., Wu, G., Yao, L., & Hu, H. (2026). Privacy-Preserving GAN for Synthetic Data against Membership Inference Attack. ACM Transactions on Privacy and Security, 29(3), 1-23. https://doi.org/10.1145/3820889

Vancouver

Cui G, Wu G, Yao L, Hu H. Privacy-Preserving GAN for Synthetic Data against Membership Inference Attack. ACM Transactions on Privacy and Security. 2026;29(3):1-23. doi:10.1145/3820889

BibTeX
@article{Cui2026,
  author = {Cui, Guizhang and Wu, Guowei and Yao, Lin and Hu, Haibo},
  title = {Privacy-Preserving GAN for Synthetic Data against Membership Inference Attack},
  journal = {ACM Transactions on Privacy and Security},
  year = {2026},
  volume = {29},
  number = {3},
  pages = {1--23},
  doi = {10.1145/3820889}
}
Kostenlos starten →