User-level Differential Privacy

User-Level Differential Privacy is a variant of differential privacy in which the privacy guarantee ensures that the output distribution of a mechanism changes by at most a multiplicative factor of exp(ε) when the data of any single user is added to or removed from the dataset, thereby protecting the contribution of an entire user regardless of the number of data points they contribute.

40

Publications

2.5K

Citations

115

Authors

56

Institutions

Publications per year

2017–2026

34

Authors

115

  1. HB
    H. Brendan McMahan

    Google (United States), United States

    6 publications · 1K citations

    6

    h-index

  2. KT
    Kunal Talwar

    Microsoft (United States), United States

    3 publications · 853 citations

    3

    h-index

  3. GA
    Galen Andrew

    Google (United States), United States

    3 publications · 163 citations

    3

    h-index

  4. DR
    Daniel Ramage

    Google (United States), United States

    3 publications · 853 citations

    3

    h-index

  5. DD
    David Durfee

    Georgia Institute of Technology, United States

    3 publications · 70 citations

    3

    h-index

1–5 of 115

Venues

  1. arXiv (Cornell University)

    Repository · 9 publications · 1K citations

    9

    h-index

  2. Computers & Security

    2 publications · 80 citations

    2

    h-index

  3. Journal of Privacy and Confidentiality

    JPC · 2 publications · 48 citations

    2

    h-index

  4. SSRN Electronic Journal

    Repository · 1 publications · 15 citations

    1

    h-index

  5. Harvard Kennedy School Misinformation Review

    1 publications · 29 citations

    1

    h-index

1–5