Enforcement of k-anonymity Through Generalization and Suppression

While limited data set is shown to not guarantee anonymity, k-anonymity is proposed by Dr. Latanya Sweeney of MIT as an alternative way to release public information while ensuring both data privacy and data integrity [1, 2, 3]. k-anonymity is provided by using generalization and suppression techniques. Generalization involves replacing a value with a less specific but semantically consistent value. Suppression involves not releasing a value at all. These techniques provide results that are minimally distorted. However, the optimization are shown to be NP-hard. Several papers respond to the k-anonymity technique by suggesting approximation algorithms that provides optimal k-anonymity in polynomial time [4, 5]. In this project, k-anonymity described in [3] is implemented using C programming language. The data protection techniques, generalization and suppression, are explored in the implementation. A data holder is able to supply the program a table in text file format and specifies the desire k value and attribute properties.