Northern Kentucky University
User-Controlled Generalization Boundaries for p-Sensitive k-Anonymity
Institution
Northern Kentucky University
Faculty Advisor/ Mentor
Alina Campa; Traian Marius Truta
Abstract
Numerous privacy models based on the k-anonymity property and extending the k-anonymity model have been introduced in the last few years in the data privacy research: l-diversity, psensitive k-anonymity, t-closeness, etc. While differing in their methods and the quality of their results, they all focus on first masking the data, then protecting the quality of the data as a whole. We considered a new approach, imposing requirements on the amount of distortion allowed on the initial data in order to preserve its usefulness. Specifying quasi-identifier generalization boundaries, we achieved p-sensitive k-anonymity within the imposed boundaries. Limiting the amount of generalization when masking microdata is indispensable for real-life datasets and applications. We defined the constrained p-sensitive k-anonymity model and presented an algorithm for generating constrained p-sensitive k-anonymous microdata. Our experiments showed that the proposed algorithm is comparable with existing algorithms used for generating p-sensitive k-anonymity with respect to the results’ quality, while the obtained masked microdata obviously complies with the user’s generalization boundaries.
User-Controlled Generalization Boundaries for p-Sensitive k-Anonymity
Numerous privacy models based on the k-anonymity property and extending the k-anonymity model have been introduced in the last few years in the data privacy research: l-diversity, psensitive k-anonymity, t-closeness, etc. While differing in their methods and the quality of their results, they all focus on first masking the data, then protecting the quality of the data as a whole. We considered a new approach, imposing requirements on the amount of distortion allowed on the initial data in order to preserve its usefulness. Specifying quasi-identifier generalization boundaries, we achieved p-sensitive k-anonymity within the imposed boundaries. Limiting the amount of generalization when masking microdata is indispensable for real-life datasets and applications. We defined the constrained p-sensitive k-anonymity model and presented an algorithm for generating constrained p-sensitive k-anonymous microdata. Our experiments showed that the proposed algorithm is comparable with existing algorithms used for generating p-sensitive k-anonymity with respect to the results’ quality, while the obtained masked microdata obviously complies with the user’s generalization boundaries.