User-level Privacy

User-Level Privacy is a privacy preservation paradigm in federated learning that belongs to the class of data protection mechanisms, specifically distinguished by ensuring that the participation of an entire user’s data—comprising all their contributed samples or interactions—cannot be distinguished or reconstructed by an adversary, even when multiple data points from the same individual are involved in the learning process.

565

Publications

33.1K

Citations

1.9K

Authors

642

Institutions

Publications per year

2017–2026

350

Authors

1.9K

  1. HB
    H. Brendan McMahan

    Google (United States), United States

    6 publications · 1K citations

    6

    h-index

  2. ZW
    Zhibo Wang

    Wuhan University, China

    6 publications · 1.3K citations

    6

    h-index

  3. QW
    Qian Wang

    Wuhan University, China

    5 publications · 1.2K citations

    5

    h-index

  4. JS
    Jinhyun So

    University of Southern California, United States

    5 publications · 417 citations

    5

    h-index

  5. QY
    Qiang Yang

    Hong Kong University of Science and Technology, Hong Kong SAR China

    4 publications · 387 citations

    4

    h-index

1–5 of 1.9K

Venues

  1. arXiv (Cornell University)

    Repository · 31 publications · 1.7K citations

    17

    h-index

  2. IEEE Access

    16 publications · 1.5K citations

    15

    h-index

  3. IEEE Internet of Things Journal

    10 publications · 907 citations

    10

    h-index

  4. 6

    h-index

  5. SSRN Electronic Journal

    Repository · 6 publications · 106 citations

    6

    h-index

1–5