P-Sensitive K-Anonymity with Generalization Constraints
Transactions on Data Privacy
On-the-fly hierarchies for numerical attributes in data anonymization
SDM'10 Proceedings of the 7th VLDB conference on Secure data management
On-the-fly generalization hierarchies for numerical attributes revisited
SDM'11 Proceedings of the 8th VLDB international conference on Secure data management
| Hi-index | 0.00 |
Recent work has shown that the adversary’s background knowledge is a very important factor in privacy-preserving data publishing. In this paper, we formalize background knowledge ħ of form “an individual X’s sensitive value belongs to class C or range R”. Through analyzing the drawbacks of previous approaches in dealing with this form of background knowledge, we develop a novel privacy criterion (τ, λ)-uniqueness that sufficiently defends against attacks leveraging the background knowledge ħ. We accompany the criterion with an effective algorithm, which computes a privacy-guarded published table that permits retrieval of accurate aggregate information about the microdata. We illustrate its advantages through theoretical analysis and experimental validation.