references.bib

@article{benedetto2018creation,
  title={The creation and use of the SIPP synthetic Beta v7. 0},
  author={Benedetto, Gary and Stanley, Jordan C and Totty, Evan and others},
  journal={US Census Bureau},
  year={2018}
}

@inproceedings{bowen2020synthetic,
  title={A synthetic supplemental public use file of low-income information return data: methodology, utility, and privacy implications},
  author={Bowen, Claire McKay and Bryant, Victoria and Burman, Leonard and Khitatrakun, Surachai and McClelland, Robert and Stallworth, Philip and Ueyama, Kyle and Williams, Aaron R},
  booktitle={International Conference on Privacy in Statistical Databases},
  pages={257--270},
  year={2020},
  organization={Springer}
}

@article{bowen2021differentially,
  title={Differentially private data release via statistical election to partition sequentially},
  author={Bowen, Claire McKay and Liu, Fang and Su, Bingyue},
  journal={Metron},
  volume={79},
  number={1},
  pages={1--31},
  year={2021},
  publisher={Springer}
}

@inproceedings{bun2016concentrated,
  title={Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds},
  author={Bun, Mark and Steinke, Thomas},
  booktitle={Theory of Cryptography Conference},
  pages={635--58},
  year={2016},
  organization={Springer}
}

@article{drecshlerjorgcomparingsynthetic,
  author = {Drechsler, Jörg and Bender, Stefan and Rässler, Susanne},
  year = {2008},
  month = {12},
  pages = {105-130},
  title = {Comparing Fully and Partially Synthetic Datasets for Statistical Disclosure Control in the German IAB Establishment Panel},
  volume = {1},
  journal = {Transactions on Data Privacy}
}

@article{drechsler2021synthesizing,
  title={Synthesizing geocodes to facilitate access to detailed geographical information in large-scale administrative data},
  author={Drechsler, J{\"o}rg and Hu, Jingchen},
  journal={Journal of Survey Statistics and Methodology},
  volume={9},
  number={3},
  pages={523--548},
  year={2021},
  publisher={Oxford University Press}
}

@article{dwork2006calibrating,
  title={Calibrating Noise to Sensitivity in Private Data Analysis},
  author={Dwork, Cynthia and McSherry, Frank and Nissim, Kobbi and Smith, Adam},
  booktitle={Theory of Cryptography},
  pages={265--84},
  year={2006},
  publisher={Springer}
}

@inproceedings{dwork2006our,
  title={Our Data, Ourselves: Privacy via Distributed Noise Generation},
  author={Dwork, Cynthia and Kenthapadi, Krishnaram and McSherry, Fang and Mironov, Ilya and Naor, Moni},
  booktitle={Annual International Conference on the Theory and Applications of Cryptographic Techniques},
  pages={486--503},
  year={2006},
  publisher={Springer}
}

@article{dwork2014algorithmic,
  title={The Algorithmic Foundations of Differential Privacy},
  author={Dwork, Cynthia and Roth, Aaron},
  journal={Foundations and Trends{\textregistered} in Theoretical Computer Science},
  volume={9},
  number={3--4},
  pages={211--407},
  year={2014},
  publisher={Now Publishers}
}

@article{dwork2016concentrated,
  title={Concentrated Differential Privacy},
  author={Dwork, Cynthia and Rothblum, Guy N},
  journal={arXiv},
  year={2016}
}

@article{fellegi1972question,
  title={On the question of statistical confidentiality},
  author={Fellegi, Ivan P},
  journal={Journal of the American Statistical Association},
  volume={67},
  number={337},
  pages={7--18},
  year={1972},
  publisher={Taylor \& Francis}
}

@inproceedings{fienberg2018statistical,
  title={Statistical Disclosure Limitation for\~{} Data\~{} Access},
  author={Fienberg, Stephen E and Jin, Jiashun},
  booktitle={Encyclopedia of Database Systems (2nd ed.)},
  year={2018}
}

@article{little1993statistical,
  title={Statistical analysis of masked data},
  author={Little, Roderick JA},
  journal={JOURNAL OF OFFICIAL STATISTICS-STOCKHOLM-},
  volume={9},
  pages={407--407},
  year={1993},
  publisher={ALMQVIST \& WIKSELL INTERNATIONAL}
}

@article{matthews2011data,
  title={Data confidentiality: A review of methods for statistical disclosure limitation and methods for assessing privacy},
  author={Matthews, Gregory J and Harel, Ofer},
  journal={Statistics Surveys},
  volume={5},
  pages={1--29},
  year={2011},
  publisher={Amer. Statist. Assoc., the Bernoulli Soc., the Inst. Math. Statist., and the~…}
}

@article{mayer2016evaluating,
  title={Evaluating the privacy properties of telephone metadata},
  author={Mayer, Jonathan and Mutchler, Patrick and Mitchell, John C},
  journal={Proceedings of the National Academy of Sciences},
  volume={113},
  number={20},
  pages={5536--5541},
  year={2016},
  publisher={National Acad Sciences}
}

@inproceedings{mcsherry2007mechanism,
  title={Mechanism Design via Differential Privacy},
  author={McSherry, Frank and Talwar, Kunal},
  booktitle={48th Annual Institute of Electrical and Electronics Engineers Symposium onFoundations of Computer Science},
  pages={94--103},
  year={2007},
  organization={Institute of Electrical and Electronics Engineers}
}

@inproceedings{mcsherry2009privacy,
  title={Privacy Integrated Queries: An Extensible Platform for Privacy-Preserving Data Analysis},
  author={McSherry, Frank D},
  booktitle={Proceedings of the 2009 Association for Computing Machinery's Special Interest Group on Management of Data International Conference on Management of Data},
  pages={19--30},
  year={2009},
  organization={Association for Computing Machinery}
}

@inproceedings{nissim2007smooth,
  title={Smooth Sensitivity and Sampling in Private Data Analysis},
  author={Nissim, Kobbi and Raskhodnikova, Sofya and Smith, Adam},
  booktitle={Proceedings of the 39th Annual Association for Computing Machinery Symposium on Theory of Computing},
  pages={75--84},
  year={2007},
  organization={Association for Computing Machinery}
}

@article{mendelevitch2021fidelity,
  title={Fidelity and privacy of synthetic medical data},
  author={Mendelevitch, Ofer and Lesh, Michael D},
  journal={arXiv preprint arXiv:2101.08658},
  year={2021}
}

@article{raghunathan2021synthetic,
  title={Synthetic data},
  author={Raghunathan, Trivellore E},
  journal={Annual Review of Statistics and Its Application},
  volume={8},
  pages={129--140},
  year={2021},
  publisher={Annual Reviews}
}

@article{rubin1977formalizing,
  title={Formalizing subjective notions about the effect of nonrespondents in sample surveys},
  author={Rubin, Donald B},
  journal={Journal of the American Statistical Association},
  volume={72},
  number={359},
  pages={538--543},
  year={1977},
  publisher={Taylor \& Francis}
}

@article{rubin1993statistical,
  title={Statistical disclosure limitation},
  author={Rubin, Donald B},
  journal={Journal of official Statistics},
  volume={9},
  number={2},
  pages={461--468},
  year={1993}
}

@article{ruggles2021role,
  title={The role of chance in the census bureau database reconstruction experiment},
  author={Ruggles, Steven and Van Riper, David},
  journal={Population Research and Policy Review},
  pages={1--8},
  year={2021},
  publisher={Springer}
}

@article{snoke2018general,
  title={General and specific utility measures for synthetic data},
  author={Snoke, Joshua and Raab, Gillian M and Nowok, Beata and Dibben, Chris and Slavkovic, Aleksandra},
  journal={Journal of the Royal Statistical Society: Series A (Statistics in Society)},
  volume={181},
  number={3},
  pages={663--688},
  year={2018},
  publisher={Wiley Online Library}
}

@article{snoke_raab_nowok_dibben_slavkovic_2018,
   title={General and specific utility measures for synthetic data},
   volume={181}, DOI={10.1111/rssa.12358},
   number={3},
   journal={Journal of the Royal Statistical Society: Series A (Statistics in Society)},
   author={Snoke, Joshua and Raab, Gillian M. and Nowok, Beata and Dibben, Chris and Slavkovic, Aleksandra},
   year={2018},
   pages={663–688}  
} 

@article{sweeney2000simple,
  title={Simple demographics often identify people uniquely},
  author={Sweeney, Latanya},
  journal={Health (San Francisco)},
  volume={671},
  number={2000},
  pages={1--34},
  year={2000}
}

@article{woo2009global,
  title={Global measures of data utility for microdata masked for disclosure limitation},
  author={Woo, Mi-Ja and Reiter, Jerome P and Oganian, Anna and Karr, Alan F},
  journal={Journal of Privacy and Confidentiality},
  volume={1},
  number={1},
  year={2009}
}

@article{reiter2009estimating,
  title={Estimating risks of identification disclosure in partially synthetic data},
  author={Reiter, Jerome P and Mitra, Robin},
  journal={Journal of Privacy and Confidentiality},
  volume={1},
  number={1},
  year={2009}
}


@article{barrientos_feasibility_2021,
	title = {A {Feasibility} {Study} of {Differentially} {Private} {Summary} {Statistics} and {Regression} {Analyses} with {Evaluations} on {Administrative} and {Survey} {Data}},
	copyright = {Creative Commons Attribution 4.0 International},
	url = {https://arxiv.org/abs/2110.12055},
	doi = {10.48550/ARXIV.2110.12055},
	abstract = {Federal administrative data, such as tax data, are invaluable for research, but because of privacy concerns, access to these data is typically limited to select agencies and a few individuals. An alternative to sharing microlevel data is to allow individuals to query statistics without directly accessing the confidential data. This paper studies the feasibility of using differentially private (DP) methods to make certain queries while preserving privacy. We also include new methodological adaptations to existing DP regression methods for using new data types and returning standard error estimates. We define feasibility as the impact of DP methods on analyses for making public policy decisions and the queries accuracy according to several utility metrics. We evaluate the methods using Internal Revenue Service data and public-use Current Population Survey data and identify how specific data features might challenge some of these methods. Our findings show that DP methods are feasible for simple, univariate statistics but struggle to produce accurate regression estimates and confidence intervals. To the best of our knowledge, this is the first comprehensive statistical study of DP regression methodology on real, complex datasets, and the findings have significant implications for the direction of a growing research field and public policy.},
	urldate = {2023-07-07},
	author = {Barrientos, Andrés F. and Williams, Aaron R. and Snoke, Joshua and Bowen, Claire McKay},
	year = {2021},
	note = {Publisher: arXiv
Version Number: 3},
	keywords = {Applications (stat.AP), FOS: Computer and information sciences},
	annote = {Other
Main: 30 pages, 3 figures, 3 tables; Supplemental: 26 pages, 14 figures, 12 tables; References: 7 pages},
}


@article{bowen2021philosophy,
  title={Philosophy of differential privacy},
  author={Bowen, Claire M and Garfinkel, Simson},
  journal={Notices of the American Mathematical Society},
  volume={68},
  number={10},
  pages={1727--39},
  year={2021}
}

@misc{us2021disclosure,
  title={Disclosure avoidance for the 2020 census: An introduction},
  author={US Census Bureau},
  year={2021},
  publisher={US Government Publishing Office Washington, DC}
}

@article{near2020differential,
  title={Differential Privacy for Privacy-Preserving Data Analysis: An Introduction to our Blog Series},
  author={Near, Joseph},
  year={2020},
  publisher={Joseph Near}
}

@inproceedings{dwork2006calibrating,
  title={Calibrating noise to sensitivity in private data analysis},
  author={Dwork, Cynthia and McSherry, Frank and Nissim, Kobbi and Smith, Adam},
  booktitle={Theory of Cryptography: Third Theory of Cryptography Conference, TCC 2006, New York, NY, USA, March 4-7, 2006. Proceedings 3},
  pages={265--284},
  year={2006},
  organization={Springer}
}

@inproceedings{bun2016concentrated,
  title={Concentrated differential privacy: Simplifications, extensions, and lower bounds},
  author={Bun, Mark and Steinke, Thomas},
  booktitle={Theory of Cryptography Conference},
  pages={635--658},
  year={2016},
  organization={Springer}
}

@inproceedings{mcsherry2009privacy,
  title={Privacy integrated queries: an extensible platform for privacy-preserving data analysis},
  author={McSherry, Frank D},
  booktitle={Proceedings of the 2009 ACM SIGMOD International Conference on Management of data},
  pages={19--30},
  year={2009}
}

@article{williams2023promise,
  title={The promise and limitations of formal privacy},
  author={Williams, Aaron R and Bowen, Claire McKay},
  journal={Wiley Interdisciplinary Reviews: Computational Statistics},
  pages={e1615},
  year={2023},
  publisher={Wiley Online Library}
}

@article{abowd20222020,
  title={The 2020 census disclosure avoidance system topdown algorithm},
  author={Abowd, John M and Ashmead, Robert and Cumings-Menon, Ryan and Garfinkel, Simson and Heineck, Micah and Heiss, Christine and Johns, Robert and Kifer, Daniel and Leclerc, Philip and Machanavajjhala, Ashwin and others},
  journal={Harvard Data Science Review},
  number={Special Issue 2},
  year={2022}
}

@article{bowen2021comparative,
  title={Comparative Study of Differentially Private Synthetic Data Algorithms from the NIST PSCR Differential Privacy Synthetic Data Challenge},
  author={Bowen, Claire McKay and Snoke, Joshua},
  journal={Journal of Privacy and Confidentiality},
  volume={11},
  number={1},
  year={2021}
}

@article{mckenna2021winning,
  title={Winning the NIST Contest: A scalable and general approach to differentially private synthetic data},
  author={McKenna, Ryan and Miklau, Gerome and Sheldon, Daniel},
  journal={arXiv preprint arXiv:2108.04978},
  year={2021}
}

@article{rogers2020linkedin,
  title={LinkedIn's Audience Engagements API: A privacy preserving data analytics system at scale},
  author={Rogers, Ryan and Subramaniam, Subbu and Peng, Sean and Durfee, David and Lee, Seunghyun and Kancha, Santosh Kumar and Sahay, Shraddha and Ahammad, Parvez},
  journal={arXiv preprint arXiv:2002.05839},
  year={2020}
}

@article{aktay2020google,
  title={Google COVID-19 community mobility reports: anonymization process description (version 1.1)},
  author={Aktay, Ahmet and Bavadekar, Shailesh and Cossoul, Gwen and Davis, John and Desfontaines, Damien and Fabrikant, Alex and Gabrilovich, Evgeniy and Gadepalli, Krishna and Gipson, Bryant and Guevara, Miguel and others},
  journal={arXiv preprint arXiv:2004.04145},
  year={2020}
}

@article{ridgeway2020crisis,
  title={Crisis collaborations: Challenges for safe data sharing with differential privacy},
  author={Ridgeway, Diane and Task, Christine and Howarth, Gary and Van Ballegooijen, David},
  journal={NIST (PSCR 2020)},
  year={2020}
}

@article{ruggles2021risk,
  title={Risk assessment procedures for the 2020 US census.},
  author={Ruggles, Steven and Cleveland, Lara and Van Riper, David},
  year={2021}
}
@article{warner1965,
	title = {Randomized Response: A Survey Technique for Eliminating Evasive Answer Bias},
	author = {Warner, Stanley L.},
	year = {1965},
	month = {03},
	date = {1965-03},
	journal = {Journal of the American Statistical Association},
	pages = {63--69},
	volume = {60},
	number = {309},
	doi = {10.1080/01621459.1965.10480775},
	url = {http://www.tandfonline.com/doi/abs/10.1080/01621459.1965.10480775},
	langid = {en}
}

@article{wang2020,
	title = {A Comprehensive Survey on Local Differential Privacy toward Data Statistics and Analysis},
	author = {Wang, Teng and Zhang, Xuefeng and Feng, Jingyu and Yang, Xinyu},
	year = {2020},
	month = {12},
	date = {2020-12-08},
	journal = {Sensors},
	pages = {7030},
	volume = {20},
	number = {24},
	doi = {10.3390/s20247030},
	url = {https://www.mdpi.com/1424-8220/20/24/7030},
	langid = {en}
}

@article{hu2023advancing,
  title={Advancing Microdata Privacy Protection: A Review of Synthetic Data},
  author={Hu, Jingchen and Bowen, Claire McKay},
  journal={arXiv preprint arXiv:2308.00872},
  year={2023}
}