Preventing Interval-Based Inference by Random Data Perturbation
Random data perturbation (RDP) method is often used in statistical databases to prevent inference of sensitive information about individuals from legitimate sum queries. In this paper, we study the RDP method for preventing an important type of inference: interval-based inference. In terms of interval-based inference, the sensitive information about individuals is said to be compromised if an accurate enough interval, called inference interval, is obtained into which the value of the sensitive information must fall. We show that the RDP methods proposed in the literature are not effective for preventing such interval-based inference. Based on a new type of random distribution, called ∊-Gaussian distribution, we propose a new RDP method to guarantee no interval-based inference.
KeywordsStatistical Inference Random Noise Tolerance Level Sensitive Information Random Perturbation
Unable to display preview. Download preview PDF.
- 3.D.E. Denning. Are statistical data bases secure? In AFIPS conference proceedings, volume 47, pages 199–204, 1978.Google Scholar
- 5.D.E. Denning and J. Schlörer. Inference controls for statistical databases. IEEE Computer, 16(7):69–82, 1983.Google Scholar
- 6.R. Fourer. Linear programming frequently asked questions. Optimization Technology Center of Northwestern University and Argonne National Laboratory, 2001. http://www-unix.mcs.anl.gov/otc/Guide/faq/linear-programming-faq.html.
- 7.N. Matloff. Another look at the use of noise addition for database security. In Proceedings of the 1986 IEEE Symposium on Security and Privacy, pages 173–180, 1986.Google Scholar
- 9.M.A. Palley. Security of statistical databases compromise through attribute correlational modeling. In Proc. of IEEE Conference on Data Engineering, pages 67–74, 1986.Google Scholar