Privbayes : private data release via Bayesian networks
- Submitting institution
-
The University of Warwick
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 5962
- Type
- D - Journal article
- DOI
-
10.1145/3134428
- Title of journal
- ACM Transactions on Database Systems
- Article number
- 25
- First page
- -
- Volume
- 42
- Issue
- 4
- ISSN
- 0362-5915
- Open access status
- Compliant
- Month of publication
- November
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
D - Data Science, Systems and Security
- Citation count
- 36
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This first work on creating private Bayesian models of data was an invited submission as one of the best papers from the leading SIGMOD 2014 conference, where the preliminary version appeared. The algorithm won 3rd prize of $10,000 in the 2018 US National Institute of Standards and Technology (NIST) Differential Privacy Synthetic Data Challenge (https://www.nist.gov/ctl/pscr/team-privbayes), and influenced the winning method (https://www.nist.gov/ctl/pscr/team-rmckenna). It is described in multiple tutorials and surveys including Soria-Comas, Domingo-Ferrer, Data Science and Engineering 2016; Machanavajjhala, He, Hay, ACM SIGMOD 2017; and Zhu, Li, Zhou, Yu, Springer 2017. The open-source code on Sourceforge (https://sourceforge.net/projects/privbayes/) has had >700 downloads.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -