Microdata Protection Flashcards
What is microdata and what type of information does it provide?
Microdata is unit-level data obtained from sample surveys, censuses, and administrative systems that provides information about the characteristics of individual people, households, businesses, facilities, farms, or geographical areas.
Microdata attributes?
Identifiers can unambiguously identify a person (e.g.,
passport number, DNI/NIE in Spain)
Quasi-identifiers identify the person with some ambiguity
(e.g., home address, telephone number)
Confidential attributes contain sensitive information (e.g.,
salary, religion, ethnicity, gender orientation, diagnosis)
Non-confidential attributes are what remains
What are global and local re-coding in non-perturbative methods for privacy protection?
Modify the data in a way that preserves the statistical properties of the original data while providing privacy guarantees.
These methods do not involve adding noise to the data, which is the main characteristic of perturbative methods.
Examples of non-perturbative methods include data swapping, microaggregation, and data clustering.
What is microaggregation as a perturbative method for privacy protection?
Partitioning the data into non-overlapping groups,
computing the mean or median for each group, and
adding random noise to the values.
resulting values are then substituted for the original data, with the aim of preserving statistical properties while protecting privacy.
Microaggregation is widely used in data disclosure control, particularly in cases where the underlying distribution is unknown.
