Skip to main content

Table 1 De-identification threats of structured data and unstructured data

From: Design of a human-centric de-identification framework for utilizing various clinical research data

Type 1. Classification 2. Processing of DID 3. Processing of QID 4. Processing of SA (optional)
Structured data
 Methods Manual (human)
Heuristic
Artificial Intelligence
Generalization, Randomization, Elimination
 Threats Mis-classification Misprocess, Single out, Likability, Inference Homogeneity attack, Background knowledge attack Similarity attack, Skewness attack
Unstructured data
 Methods Manual (human)
Heuristic
Artificial Intelligent
Cryptography, Replacement, Elimination
 Threats Mis-classification Misprocess, Single out, Likability, Inference