.png){kind=icon}
Return
DP-GAN: Differentially private consecutive data publishing using generative adversarial nets
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jnca.2021.103066.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In the era of big data, increasingly massive volumes of data is generated and published consecutively for both research and commercial purposes. The potential value of sensitive information also attracts interest from adversaries and thereby arises public concern. Current research mostly focuses on privacy-preserving data publishing in a statistic manner rather than taking the dynamics and correlation of context into consideration. Motivated by this, we propose a novel idea that combining differential privacy and generative adversarial nets. Generative adversarial nets and its extensions are used to generate a synthetic dataset with indistinguishable statistic features while differential privacy guarantees a trade-off between privacy protection and data utility. By employing a min-max game with three players, we devise a deep generative model, namely DP-GAN model, for synthetic data generation while fulfilling the privacy constraints in a differentially private manner. Extensive simulation results on a real-world dataset testify the superiority of the proposed model in terms of privacy protection, data utility, and efficiency.
Keywords:
Continual data release
Differential privacy
Generative adversarial nets
Journal
IF:
8
Papers:
3.7K
Citations:
1.1W
Organization
Cited Papers
.png){kind=icon}
Individual Differential Privacy: A Utility-Preserving Formulation of Differential Privacy Guarantees
OAAI
OAAIShareSaveShareSaveShareSave no more
no more