Description

Preserving the utility of published datasets while simultaneously providing provable privacy guarantees is a well-known challenge. On the one hand, context-free privacy solutions, such as differential privacy, provide strong privacy

Preserving the utility of published datasets while simultaneously providing provable privacy guarantees is a well-known challenge. On the one hand, context-free privacy solutions, such as differential privacy, provide strong privacy guarantees, but often lead to a significant reduction in utility. On the other hand, context-aware privacy solutions, such as information theoretic privacy, achieve an improved privacy-utility tradeoff, but assume that the data holder has access to dataset statistics.

Reuse Permissions
  • application/pdf

    Download count: 0

    Details

    Contributors
    Date Created
    • 2017-12-01
    Resource Type
  • Text
  • Collections this item is in
    Identifier
    • Digital object identifier: 10.3390/e19120656
    • Identifier Type
      International standard serial number
      Identifier Value
      1099-4300

    Citation and reuse

    Cite this item

    This is a suggested citation. Consult the appropriate style guide for specific citation guidelines.

    Huang, C., Kairouz, P., Chen, X., Sankar, L., & Rajagopal, R. (2017). Context-Aware Generative Adversarial Privacy. Entropy, 19(12), 656. doi:10.3390/e19120656

    Machine-readable links