Multimethod synthetic data generation for confidentiality and measurement of disclosure risk.
Michael D. LarsenJennifer C. HuckettPublished in: Int. J. Inf. Priv. Secur. Integr. (2012)
Keyphrases
- data generation
- disclosure risk
- statistical disclosure control
- statistical agencies
- information loss
- tabular data
- record linkage
- confidential information
- confidential data
- data protection
- contingency tables
- numerical data
- active learning
- statistical databases
- streaming data
- statistical information
- information content
- data streams
- access control
- data sets
- high throughput
- data acquisition
- co training
- information security
- multi view
- probabilistic model
- learning algorithm