Universally utility-maximizing privacy mechanisms

ABSTRACT

A mechanism for releasing information about a statistical database with sensitive data must resolve a trade-off between utility and privacy. Publishing fully accurate information maximizes utility while minimizing privacy, while publishing random noise accomplishes the opposite. Privacy can be rigorously quantified using the framework of differential privacy, which requires that a mechanism's output distribution is nearly the same whether or not a given database row is included or excluded. The goal of this paper is strong and general utility guarantees, subject to differential privacy. We pursue mechanisms that guarantee near-optimal utility to every potential user, independent of its side information (modeled as a prior distribution over query results) and preferences (modeled via a loss function). Our main result is: for each fixed count query and differential privacy level, there is a geometric mechanism M* -- a discrete variant of the simple and well-studied Laplace mechanism -- that is simultaneously expected loss-minimizing for every possible user, subject to the differential privacy constraint. This is an extremely strong utility guarantee: every potential user u, no matter what its side information and preferences, derives as much utility from M* as from interacting with a differentially private mechanism M_u that is optimally tailored to u. More precisely, for every user u there is an optimal mechanism M_u for it that factors into a user-independent part (the geometric mechanism M*) followed by user-specific post-processing that can be delegated to the user itself. The first part of our proof of this result characterizes the optimal differentially private mechanism for a fixed but arbitrary user in terms of a certain basic feasible solution to a linear program with constraints that encode differential privacy. The second part shows that all of the relevant vertices of this polytope (ranging over all possible users) are derivable from the geometric mechanism via suitable remappings of its range.

REFERENCES

• 1: Lars Backstrom , Cynthia Dwork , Jon Kleinberg, Wherefore art thou r3579x?: anonymized social networks, hidden patterns, and structural steganography, Proceedings of the 16th international conference on World Wide Web, May 08-12, 2007, Banff, Alberta, Canada [doi>10.1145/1242572.1242598]
• 2: Boaz Barak , Kamalika Chaudhuri , Cynthia Dwork , Satyen Kale , Frank McSherry , Kunal Talwar, Privacy, accuracy, and consistency too: a holistic solution to contingency table release, Proceedings of the twenty-sixth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems, June 11-13, 2007, Beijing, China [doi>10.1145/1265530.1265569]
• 3: Dimitris Bertsimas , John Tsitsiklis, Introduction to Linear Optimization, Athena Scientific, 1997
• 4: Avrim Blum , Cynthia Dwork , Frank McSherry , Kobbi Nissim, Practical privacy: the SuLQ framework, Proceedings of the twenty-fourth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems, June 13-15, 2005, Baltimore, Maryland [doi>10.1145/1065167.1065184]
• 5: Avrim Blum , Katrina Ligett , Aaron Roth, A learning theory approach to non-interactive database privacy, Proceedings of the 40th annual ACM symposium on Theory of computing, May 17-20, 2008, Victoria, British Columbia, Canada [doi>10.1145/1374376.1374464]
• 6: U.S. Census Bureau. The 2008 statistical abstract. http://www.census.gov/compendia/statab/.
• 7: Irit Dinur , Kobbi Nissim, Revealing information while preserving privacy, Proceedings of the twenty-second ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems, p.202-210, June 09-11, 2003, San Diego, California [doi>10.1145/773153.773173]
• 8: C. Dwork. Differential privacy. In Proceedings of the 33rd Annual International Colloquium on Automata, Languages, and Programming (ICALP), volume 4051 of Lecture Notes in Computer Science, pages 1--12, 2006.
• 9: C. Dwork. Differential privacy: A survey of results. In 5th International Conference on Theory and Applications of Models of Computation (TAMC), volume 4978 of Lecture Notes in Computer Science, pages 1--19, 2008.
• 10: C. Dwork, F. McSherry, K. Nissim, and A. Smith. Calibrating noise to sensitivity in private data analysis. In Third Theory of Cryptography Conference (TCC), volume 3876 of Lecture Notes in Computer Science, pages 265--284, 2006.
• 11: Cynthia Dwork , Frank McSherry , Kunal Talwar, The price of privacy and the limits of LP decoding, Proceedings of the thirty-ninth annual ACM symposium on Theory of computing, June 11-13, 2007, San Diego, California, USA [doi>10.1145/1250790.1250804]
• 12: C. Dwork and K. Nissim. Privacy-preserving datamining on vertically partitioned databases. In 24th Annual International Cryptology Conference (CRYPTO), volume 3152 of Lecture Notes in Computer Science, pages 528--544, 2004.
• 13: Shiva Prasad Kasiviswanathan , Homin K. Lee , Kobbi Nissim , Sofya Raskhodnikova , Adam Smith, What Can We Learn Privately?, Proceedings of the 2008 49th Annual IEEE Symposium on Foundations of Computer Science, p.531-540, October 25-28, 2008 [doi>10.1109/FOCS.2008.27]
• 14: S. P. Kasiviswanathan and A. Smith. A note on differential privacy: Defining resistance to arbitrary side information. http://arxiv.org/abs/0803.3946v1, 2008.
• 15: A. Mas-Colell, M. D. Whinston, and J. R. Green. Microeconomic Theory. Oxford University Press, New York, 1995.
• 16: Frank McSherry , Kunal Talwar, Mechanism Design via Differential Privacy, Proceedings of the 48th Annual IEEE Symposium on Foundations of Computer Science, p.94-103, October 21-23, 2007 [doi>10.1109/FOCS.2007.41]
• 17: Arvind Narayanan , Vitaly Shmatikov, Robust De-anonymization of Large Sparse Datasets, Proceedings of the 2008 IEEE Symposium on Security and Privacy, p.111-125, May 18-21, 2008 [doi>10.1109/SP.2008.33]
• 18: Kobbi Nissim , Sofya Raskhodnikova , Adam Smith, Smooth sensitivity and sampling in private data analysis, Proceedings of the thirty-ninth annual ACM symposium on Theory of computing, June 11-13, 2007, San Diego, California, USA [doi>10.1145/1250790.1250803]
• 19: Wikipedia. AOL search data scandal. http://en.wikipedia.org/wiki/AOL_search_data_scandal.

INDEX TERMS

Primary Classification:
  F. Theory of Computation
  F.0 GENERAL

General Terms:
Algorithms, Economics, Security, Theory

Keywords:
differential privacy, linear programming, privacy, utility