TR2013-028

On the Benefits of Sampling in Privacy Preserving Statistical Analysis on Distributed Databases


    •  Lin, B.-R.; Wang, Y.; Rane, S., "On the Benefits of Sampling in Privacy Preserving Statistical Analysis on Distributed Databases," Tech. Rep. TR2013-028, arXiv, April 2013.
      BibTeX Download PDF
      • @techreport{Lin2013apr2,
      • author = {Lin, B.-R. and Wang, Y. and Rane, S.},
      • title = {On the Benefits of Sampling in Privacy Preserving Statistical Analysis on Distributed Databases},
      • journal = {arXiv},
      • year = 2013,
      • month = apr,
      • url = {http://www.merl.com/publications/TR2013-028}
      • }
  • MERL Contact:
  • Research Areas:

    Information Security, Multimedia


We consider a problem where mutually untrusting curators possess portions of a vertically partitioned database containing information about a set of individuals. The goal is to enable an authorized party to obtain aggregate (statistical) information from the database while protecting the privacy of the individuals, which we formalize using Differential Privacy. This process can be facilitated by an untrusted server that provides storage and processing services but should not learn anything about the database. This work describes a data release mechanism that employs Post Randomization (PRAM), encryption and random sampling to maintain privacy, while allowing the authorized party to conduct an accurate statistical analysis of the data. Encryption ensures that the storage server obtains no information about the database, while PRAM and sampling ensures individual privacy is maintained against the authorized party. We characterize how much the composition of random sampling with PRAM increases the differential privacy of system compared to using PRAM alone. We also analyze the statistical utility of our system, by bounding the estimation error--the expected '2-norm error between the true empirical distribution and the estimated distribution--as a function of the number of samples, PRAM noise, and other system parameters. Our analysis shows a tradeoff between increasing PRAM noise versus decreasing the number of samples to maintain a desired level of privacy, and we determine the optimal number of samples that balances this tradeoff and maximizes the utility. In experimental simulations with the UCI "Adult Data Set" and with synthetically generated data, we confirm that the theoretically predicted optimal number of samples indeed achieves close to the minimal empirical error, and that our analytical error bounds match well with the empirical results.