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
Parents
40
Learning Differentially Private Recurrent Language Models
H. Brendan McMahan, Daniel Ramage, Kunal Talwar et al. · arXiv (Cornell University) · 2017 · 671 citations · Full text
Learning Differentially Private Recurrent Language Models
H. Brendan McMahan, Daniel Ramage, Kunal Talwar et al. · arXiv (Cornell University) · 2017 · 104 citations · Full text
Differentially Private Learning with Adaptive Clipping
Galen Andrew, Om Thakkar, H. Brendan McMahan et al. · arXiv (Cornell University) · 2019 · 89 citations · Full text
1–5 of 40
115
6
h-index
3
h-index
3
h-index
3
h-index
3
h-index
1–5 of 115
56
Google (United States)
Mountain View, United States
5 h-index
12 publications
962 citations

Data61
Sydney, Australia
3 h-index
4 publications
362 citations
Princeton University
Princeton, United States
3 h-index
4 publications
566 citations
University of Southern California
Los Angeles, United States
3 h-index
7 publications
246 citations
Wuhan University
Wuhan, China
2 h-index
6 publications
432 citations
Tsinghua University
Beijing, China
2 h-index
4 publications
568 citations
University of Pennsylvania
Philadelphia, United States
2 h-index
4 publications
62 citations
California Southern University
Chandler, United States
2 h-index
4 publications
138 citations
1–8 of 56
Repository · 9 publications · 1K citations
9
h-index
2 publications · 80 citations
2
h-index
JPC · 2 publications · 48 citations
2
h-index
Repository · 1 publications · 15 citations
1
h-index
1 publications · 29 citations
1
h-index
1–5