Table 3.

Comparison of reconstruction and heuristic-based PP techniques

PropertyReconstruction-based techniquesHeuristic-based techniques
DefinitionModify raw data to allow reconstruction by data collectorAlter records before public release for anonymity
ExamplesRandomisation, data swapping, synthetic data generationk-anonymity, l-diversity, t-closeness
Data utilityPreserves data utility, suitable for ML-based analysisMay result in loss of data utility due to anonymisation
ML algorithm requirementMay require specific ML algorithms but preserves data utility effectivelyMay require adjustments for certain ML algorithms due to anonymisation
SuitabilityProtects individual data points, useful when data collector is untrustworthyEffective for public data sharing while protecting individual identities
ComplexityVaries based on perturbation type and dataset sizeDepends on specific heuristic used and level of anonymisation
Computational overheadMay have higher overhead due to individual perturbationGenerally lower overhead compared to reconstruction-based techniques
Source (s): Authors’ own work

or Create an Account

Close Modal
Close Modal