"Quantifying identifiability to choose and audit epsilon in differentially ..."

Daniel Bernau et al. (2021)

> Home

Details and statistics

DOI: 10.14778/3484224.3484231

access: open

type: Journal Article

metadata version: 2022-04-21

- view
  - electronic edition @ vldb.org (open access)
  - electronic edition via DOI
  authority control:
- export record
  dblp key:
  - journals/pvldb/BernauEGKK21
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/pvldb/BernauEGKK21
Daniel Bernau, Günther Eibl, Philip-William Grassal, Hannah Keller, Florian Kerschbaum:
Quantifying identifiability to choose and audit epsilon in differentially private deep learning. Proc. VLDB Endow. 14(13): 3335-3347 (2021)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.