Differential Privacy

Differential Privacy is a formal privacy-preserving framework that belongs to the class of mathematical definitions of data confidentiality, distinguished by its guarantee that the inclusion or exclusion of a single individual’s data in a dataset has a negligible impact on the probability distribution of the output of any analysis performed on that dataset.

3.7K

Publications

240.6K

Citations

8K

Authors

1.7K

Institutions

Publications per year

2017–2026

2.6K

Authors

8K

  1. LX
    Li Xiong

    Emory University, United States

    41 publications · 2.7K citations

    30

    h-index

  2. XX
    Xiaokui Xiao

    Nanyang Technological University, Singapore

    39 publications · 4.8K citations

    29

    h-index

  3. AT
    Abhradeep Thakurta

    Google (United States), United States

    40 publications · 3K citations

    27

    h-index

  4. KT
    Kunal Talwar

    Microsoft (United States), United States

    33 publications · 10.4K citations

    27

    h-index

  5. NL
    Ninghui Li

    Purdue University West Lafayette, United States

    33 publications · 3K citations

    24

    h-index

1–5 of 8K

Venues

  1. arXiv (Cornell University)

    Repository · 486 publications · 21.5K citations

    66

    h-index

  2. Information Sciences

    88 publications · 4.7K citations

    40

    h-index

  3. 40

    h-index

  4. Proceedings of the VLDB Endowment

    PVLDB · 56 publications · 4.7K citations

    37

    h-index

  5. IEEE Internet of Things Journal

    71 publications · 5.1K citations

    36

    h-index

1–5