L-diversity

Overview

L-diversity is a privacy model for data anonymization.

L-diversity adds the requirement that each group of records must also have at least l distinct values for each sensitive attribute. This ensures that the sensitive attributes are not all the same within each group, which makes it more difficult for an attacker to identify individuals in the dataset.

Higher the value of L means, dataset provide better privacy.

To annonymize data using l diversity follow these steps 

• need to identify the QIs and sensitive attributes in your dataset. 

• You then need to choose a value for l.