Abstract
These attacks on statistical databases are no longer a theoretical danger.
- Adam, N.R., Worthmann, J.C. Security-control methods for statistical databases: A comparative study. ACM Computing Surveys 21, 4 (1989), 515--556 Google ScholarDigital Library
- Biere, A. PicoSAT essentials. J. Satisfiability, Boolean Modeling and Computation 4, (2008), 75--97; https://bit.ly/2QcziqWGoogle ScholarCross Ref
- Blum, A., Dwork, C., McSherry, F. Nissim, K. Practical privacy: The SuLQ framework. In Proceedings of the 24<sup>th</sup> ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems, 2005, 128--138; https://dl.acm.org/citation.cfm?id=1065184. Google ScholarDigital Library
- Dinur, I., Nissim, K. Revealing information while preserving privacy. In Proceedings of the 22<sup>nd</sup> ACM SIGMOD-SIGACT-SIGART Principles of Database Systems, 2003, 202--210; https://dl.acm.org/citation.cfm?id=773173. Google ScholarDigital Library
- Dwork, C., McSherry, F., Nissim, K., Smith, A. 2006. Calibrating noise to sensitivity in private data analysis. In Proceedings of the 3<sup>rd</sup> Conference on Theory of Cryptography, 2006, 265--284. Springer-Verlag, Berlin, Heidelberg Google ScholarDigital Library
- Dwork, C., Nissim, K. Privacy-preserving datamining on vertically partitioned databases. In Proceedings of the 24<sup>th</sup> International Cryptology Conference 3152, 2004, 528--544. Springer Verlag, Santa Barbara, CA; https://bit.ly/2zKunmJGoogle ScholarCross Ref
- Heule, M.J.H., Kullmann, O. The science of brute force. Commun. ACM 60, 8 (Aug. 2017), 70--79 Google ScholarDigital Library
- Kleinberg, J., Papadimitriou, C., Raghavan, P. Auditing Boolean attributes. In Proceedings of the 19<sup>th</sup> ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems, 2000, 86--91 Google ScholarDigital Library
- Kong, S., Malec, D. Cook-Levin theorem. Lecture, University of Wisconsin, 2007.Google Scholar
- Marques-Silva, J., Lynce, I., Malik, S. Conflict-driven clause learning SAT solvers. Handbook of Satisfiability, 131--153. IOS Press, Amsterdam, The Netherlands, 2009.Google Scholar
- McCarthy, J. Recursive functions of symbolic expressions and their computation by machine, part I. Commun. ACM 3, 4 (Apr. 1960), 184--195; https://dl.acm.org/citation.cfm?id=367199. Google ScholarDigital Library
- Metin, H., Baarir, S., Colange, M., Kordon, F. CDCLSym: Introducing effective symmetry breaking in SAT solving. Tools and Algorithms for the Construction and Analysis of Systems. D. Beyer and M. Huisman, eds. Springer International Publishing, 2018, 99--114; https://link.springer.com/chapter/10.1007/978-3-319-89960-2_6.Google Scholar
- Tamura, N., Taga, A., Kitagawa, S., Banbara, M. Compiling finite linear CSP into SAT. Contraints 14, 2 (2009), 254--272; https://dl.acm.org/citation.cfm?id=1527316; http://bach.istc.kobe-u.ac.jp/sugar/. Google ScholarDigital Library
- Whitney, C.R. Jeanne Calment, world's elder, dies at 122. New York Times (Aug. 5, 1997); https://nyti.ms/2kM4oFb.Google Scholar
- Zayatz, L., Lucero, J., Massell, P., Ramanayake, A. Disclosure avoidance for Census 2010 and American Community Survey five-year tabular data products. Statistical Research Division, U.S. Census Bureau; https://www.census.gov/srd/CDAR/rrs2009-10_ACS_5yr.pdf.Google Scholar
Index Terms
- Understanding database reconstruction attacks on public data
Recommendations
Understanding Database Reconstruction Attacks on Public Data: These attacks on statistical databases are no longer a theoretical danger.
BenchmarkingWith the dramatic improvement in both computer speeds and the efficiency of SAT and other NP-hard solvers in the last decade, DRAs on statistical databases are no longer just a theoretical danger. The vast quantity of data products published by ...
Subpopulation Data Poisoning Attacks
CCS '21: Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications SecurityMachine learning systems are deployed in critical settings, but they might fail in unexpected ways, impacting the accuracy of their predictions. Poisoning attacks against machine learning induce adversarial modification of data used by a machine ...
Comments