An Algorithm of K-anonymity for Data Releasing Based on Fine-grained Generalization

摘要

In recent years, publishing data about individuals without revealing their identity information has become an active issue, and k-anonymity-based models are effective techniques that prevent linking attack. Existing k-anonymity algorithms did not cope with information loss in released data set well. The paper proposes an improved algorithm FK-anonymity. Taking data distribution into account, FK-anonymity revises the generalization hierarchy according to application domain, and then generalizes original table on modified generalization hierarchy structure which increases data quality of released table. Theoretical analysis and experimental results testify the scheme is effective and can preserve privacy of the sensitive data well meanwhile maintain better data utility.