CISPA
Browse

File(s) not publicly available

GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators

conference contribution
posted on 2023-11-29, 18:14 authored by Dingfan Chen, Tribhuvanesh Orekondy, Mario FritzMario Fritz
The wide-spread availability of rich data has fueled the growth of machine learning applications in numerous domains. However, growth in domains with highly-sensitive data (e.g., medical) is largely hindered as the private nature of data prohibits it from being shared. To this end, we propose Gradient-sanitized Wasserstein Generative Adversarial Networks (GS-WGAN), which allows releasing a sanitized form of the sensitive data with rigorous privacy guarantees. In contrast to prior work, our approach is able to distort gradient information more precisely, and thereby enabling training deeper models which generate more informative samples. Moreover, our formulation naturally allows for training GANs in both centralized and federated (i.e., decentralized) data scenarios. Through extensive experiments, we find our approach consistently outperforms state-of-the-art approaches across multiple metrics (e.g., sample quality) and datasets.

History

Preferred Citation

Dingfan Chen, Tribhuvanesh Orekondy and Mario Fritz. GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators. In: Conference on Neural Information Processing Systems (NeurIPS). 2020.

Primary Research Area

  • Trustworthy Information Processing

Name of Conference

Conference on Neural Information Processing Systems (NeurIPS)

Legacy Posted Date

2020-10-04

Open Access Type

  • Gold

BibTeX

@inproceedings{cispa_all_3236, title = "GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators", author = "Chen, Dingfan and Orekondy, Tribhuvanesh and Fritz, Mario", booktitle="{Conference on Neural Information Processing Systems (NeurIPS)}", year="2020", }

Usage metrics

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC