Research Article
Quasi-Identifier Recognition Algorithm for Privacy Preservation of Cloud Data Based on Risk Reidentification
Algorithm 1
Attribute classification.
Input: dataset , ,. | Output: classified dataset. | 1: //Compute-distinct for all dataset tuples for each attribute. | 2: -distinct of the attribute () | 3: attribute domain | 4: tuple domain | 5: | 6: | 7: | 8: | 9: Fordo | 10: Fordo | 11: | 12: ; | 13: ; | 14: End | 15: ; | 16: end | 17: //Compute reidentification risk rate for all dataset attributes. | 18: | 19: reidentification risk rate of Attr | 20: Fordo | 21: For to .length do | 22: | 23: ; | 24: End | 25: ; | 26: End | 27: //Classify the attributes based on risk rate and threshold values. | 28: | 29: | 30: | 31: Fordo | 32: If | 33: ; | 34: Else If | 35: ; | 36: Else | 37: ; | 38: ; | 39: end | 40: Return |
|