CISPA
Browse

File(s) not publicly available

Private Set Generation with Discriminative Information

conference contribution
posted on 2023-11-29, 18:23 authored by Dingfan ChenDingfan Chen, Raouf KerkoucheRaouf Kerkouche, Mario FritzMario Fritz
Differentially private data generation techniques have become a promising solution to the data privacy challenge –– it enables sharing of data while complying with rigorous privacy guarantees, which is essential for scientific progress in sensitive domains. Unfortunately, restricted by the inherent complexity of modeling high-dimensional distributions, existing private generative models are struggling with the utility of synthetic samples. In contrast to existing works that aim at fitting the complete data distribution, we directly optimize for a small set of samples that are representative of the distribution, which is generally an easier task and more suitable for private training. Moreover, we exploit discriminative information from downstream tasks to further ease the training. Our work provides an alternative view for differentially private generation of high-dimensional data and introduces a simple yet effective method that greatly improves the sample utility of state-of-the-art approaches.

History

Preferred Citation

Dingfan Chen, Raouf Kerkouche and Mario Fritz. Private Set Generation with Discriminative Information. In: Conference on Neural Information Processing Systems (NeurIPS). 2022.

Primary Research Area

  • Trustworthy Information Processing

Name of Conference

Conference on Neural Information Processing Systems (NeurIPS)

Legacy Posted Date

2022-10-12

Open Access Type

  • Gold

BibTeX

@inproceedings{cispa_all_3815, title = "Private Set Generation with Discriminative Information", author = "Chen, Dingfan and Kerkouche, Raouf and Fritz, Mario", booktitle="{Conference on Neural Information Processing Systems (NeurIPS)}", year="2022", }

Usage metrics

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC