ALIASED AS Local recoding with the size of the equivalence class fixed to the size of multiples of k

4 quasi-identifiers: workclass, dob, education, education number

The lattice is constructed here as well, but it is extremely time consuming, and hence not a good idea, some optimisation on the lattice is needed here

Algorithm :

• Generalization lattice is used here, and the concept of local recoding is applied here. The existence of k-anonymity is checked, and a strict condition for the equivalence class size to be a multiple of k is imposed here.
• For tuples that do not form a part of any equivalence class, they are generalised to the highest level, thus preserving all the tuples, and no loss of data.

The multiple of k rule is very important to tackle temporal attack as no records will ever be left in odd values, thus reducing the chance of occurrence of temporal attack

(3, 0, 0, 0) 8

(3, 3, 0, 0) 4

(3, 3, 1, 3) 4

(3, 3, 2, 3) 8

(3, 5, 3, 3) 4

(4, 5, 3, 3) 8

(5, 5, 3, 4) 8

(5, 5, 4, 4) 6