{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T02:17:28Z","timestamp":1776997048416,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,27]],"date-time":"2019-10-27T00:00:00Z","timestamp":1572134400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1351089,CNS-1514437,CCF-1740833"],"award-info":[{"award-number":["CNS-1351089,CNS-1514437,CCF-1740833"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,10,27]]},"DOI":"10.1145\/3341301.3359639","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T13:34:22Z","timestamp":1571664862000},"page":"181-195","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":23,"title":["Privacy accounting and quality control in the sage differentially private ML platform"],"prefix":"10.1145","author":[{"given":"Mathias","family":"L\u00e9cuyer","sequence":"first","affiliation":[{"name":"Columbia University"}]},{"given":"Riley","family":"Spahn","sequence":"additional","affiliation":[{"name":"Columbia University"}]},{"given":"Kiran","family":"Vodrahalli","sequence":"additional","affiliation":[{"name":"Columbia University"}]},{"given":"Roxana","family":"Geambasu","sequence":"additional","affiliation":[{"name":"Columbia University"}]},{"given":"Daniel","family":"Hsu","sequence":"additional","affiliation":[{"name":"Columbia University"}]}],"member":"320","published-online":{"date-parts":[[2019,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"https:\/\/www.kaggle.com\/c\/criteo-display-ad-challenge","year":"2014","unstructured":"Kaggle display advertising challenge dataset. https:\/\/www.kaggle.com\/c\/criteo-display-ad-challenge , 2014 . Kaggle display advertising challenge dataset. https:\/\/www.kaggle.com\/c\/criteo-display-ad-challenge, 2014."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978355"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1265530.1265569"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098021"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2808769.2808775"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2011.40"},{"key":"e_1_3_2_1_8_1","volume-title":"The secret sharer: Evaluating and testing unintended memorization in neural networks. arXiv:1802.08232","author":"Carlini N.","year":"2018","unstructured":"N. Carlini , C. Liu , U. Erlingsson , J. Kos , and D. Song . The secret sharer: Evaluating and testing unintended memorization in neural networks. arXiv:1802.08232 , 2018 . N. Carlini, C. Liu, U. Erlingsson, J. Kos, and D. Song. The secret sharer: Evaluating and testing unintended memorization in neural networks. arXiv:1802.08232, 2018."},{"key":"e_1_3_2_1_9_1","author":"Chan T.-H. H.","year":"2011","unstructured":"T.-H. H. Chan , E. Shi , and D. Song . Private and continual release of statistics. ACM Transactions on Information Systems Security , 2011 . T.-H. H. Chan, E. Shi, and D. Song. Private and continual release of statistics. ACM Transactions on Information Systems Security, 2011.","journal-title":"Private and continual release of statistics. ACM Transactions on Information Systems Security"},{"key":"e_1_3_2_1_10_1","volume-title":"Proc. of the Conference on Neural Information Processing Systems (NeurIPS)","author":"Chaudhuri K.","year":"2008","unstructured":"K. Chaudhuri and C. Monteleoni . Privacy-preserving logistic regression . In Proc. of the Conference on Neural Information Processing Systems (NeurIPS) , 2008 . K. Chaudhuri and C. Monteleoni. Privacy-preserving logistic regression. In Proc. of the Conference on Neural Information Processing Systems (NeurIPS), 2008."},{"key":"e_1_3_2_1_11_1","first-page":"14","author":"Chaudhuri K.","year":"2013","unstructured":"K. Chaudhuri , A. D. Sarwate , and K. Sinha . A near-optimal algorithm for differentially-private principal components. Journal of Machine Learning Research (JMLR) , 14 , 2013 . K. Chaudhuri, A. D. Sarwate, and K. Sinha. A near-optimal algorithm for differentially-private principal components. Journal of Machine Learning Research (JMLR), 14, 2013.","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"e_1_3_2_1_12_1","volume-title":"Proc. of the Conference on Neural Information Processing Systems (NeurIPS)","author":"Cummings R.","year":"2018","unstructured":"R. Cummings , S. Krehbiel , K. A. Lai , and U. Tantipongpipat . Differential privacy for growing databases . In Proc. of the Conference on Neural Information Processing Systems (NeurIPS) , 2018 . R. Cummings, S. Krehbiel, K. A. Lai, and U. Tantipongpipat. Differential privacy for growing databases. In Proc. of the Conference on Neural Information Processing Systems (NeurIPS), 2018."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/773153.773173"},{"key":"e_1_3_2_1_14_1","volume-title":"Lower bounds for locally private estimation via communication complexity. arXiv:1902.00582","author":"Duchi J.","year":"2019","unstructured":"J. Duchi and R. Rogers . Lower bounds for locally private estimation via communication complexity. arXiv:1902.00582 , 2019 . J. Duchi and R. Rogers. Lower bounds for locally private estimation via communication complexity. arXiv:1902.00582, 2019."},{"key":"e_1_3_2_1_15_1","author":"Duchi J. C.","year":"2018","unstructured":"J. C. Duchi , M. I. Jordan , and M. J. Wainwright . Minimax optimal procedures for locally private estimation. Journal of the American Statistical Association , 2018 . J. C. Duchi, M. I. Jordan, and M. J. Wainwright. Minimax optimal procedures for locally private estimation. Journal of the American Statistical Association, 2018.","journal-title":"Journal of the American Statistical Association"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/1873601.1873617"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/11681878_14"},{"key":"e_1_3_2_1_18_1","volume-title":"Proc. of The Symposium on Innovations in Computer Science","author":"Dwork C.","year":"2010","unstructured":"C. Dwork , M. Naor , T. Pitassi ,, and S. Yekhanin . Pan-private streaming algorithms . In Proc. of The Symposium on Innovations in Computer Science , 2010 . C. Dwork, M. Naor, T. Pitassi,, and S. Yekhanin. Pan-private streaming algorithms. In Proc. of The Symposium on Innovations in Computer Science, 2010."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1806689.1806787"},{"key":"e_1_3_2_1_20_1","volume-title":"Foundations and Trends\u00ae in Theoretical Computer Science","author":"Dwork C.","year":"2014","unstructured":"C. Dwork and A. Roth . The algorithmic foundations of differential privacy . Foundations and Trends\u00ae in Theoretical Computer Science , 2014 . C. Dwork and A. Roth. The algorithmic foundations of differential privacy. Foundations and Trends\u00ae in Theoretical Computer Science, 2014."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2010.12"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-060116-054123"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2015.46"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00059"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgen.1000167"},{"key":"e_1_3_2_1_26_1","volume-title":"Proc. of USENIX Security","author":"Jayaraman B.","year":"2019","unstructured":"B. Jayaraman and D. Evans . Evaluating differentially private machine learning in practice . In Proc. of USENIX Security , 2019 . B. Jayaraman and D. Evans. Evaluating differentially private machine learning in practice. In Proc. of USENIX Security, 2019."},{"key":"e_1_3_2_1_27_1","volume-title":"International Conference on Machine Learning (ICML)","author":"Kairouz P.","year":"2015","unstructured":"P. Kairouz , S. Oh , and P. Viswanath . The composition theorem for differential privacy . In International Conference on Machine Learning (ICML) , 2015 . P. Kairouz, S. Oh, and P. Viswanath. The composition theorem for differential privacy. In International Conference on Machine Learning (ICML), 2015."},{"key":"e_1_3_2_1_28_1","author":"Kasiviswanathan S. P.","year":"2011","unstructured":"S. P. Kasiviswanathan , H. K. Lee , K. Nissim , S. Raskhodnikova , and A. Smith . What can we learn privately? SIAM Journal on Computing , 2011 . S. P. Kasiviswanathan, H. K. Lee, K. Nissim, S. Raskhodnikova, and A. Smith. What can we learn privately? SIAM Journal on Computing, 2011.","journal-title":"SIAM Journal on Computing"},{"key":"e_1_3_2_1_29_1","author":"Kasiviswanathan S. P.","year":"2014","unstructured":"S. P. Kasiviswanathan and A. Smith . On the'semantics' of differential privacy: A bayesian formulation. Journal of Privacy and Confidentiality , 2014 . S. P. Kasiviswanathan and A. Smith. On the'semantics' of differential privacy: A bayesian formulation. Journal of Privacy and Confidentiality, 2014.","journal-title":"Journal of Privacy and Confidentiality"},{"key":"e_1_3_2_1_30_1","volume-title":"Proc. of the ACM Conference on Learning Theory (COLT)","author":"Kifer D.","year":"2012","unstructured":"D. Kifer , A. Smith , and A. Thakurta . Private convex empirical risk minimization and high-dimensional regression . In Proc. of the ACM Conference on Learning Theory (COLT) , 2012 . D. Kifer, A. Smith, and A. Thakurta. Private convex empirical risk minimization and high-dimensional regression. In Proc. of the ACM Conference on Learning Theory (COLT), 2012."},{"key":"e_1_3_2_1_31_1","volume-title":"Privacy accounting and quality control in the sage differentially private ML platform. Online Supplements (also available on https:\/\/arxiv.org\/abs\/1909.01502)","author":"Lecuyer M.","year":"2019","unstructured":"M. Lecuyer , R. Spahn , K. Vodrahalli , R. Geambasu , and D. Hsu . Privacy accounting and quality control in the sage differentially private ML platform. Online Supplements (also available on https:\/\/arxiv.org\/abs\/1909.01502) , 2019 . M. Lecuyer, R. Spahn, K. Vodrahalli, R. Geambasu, and D. Hsu. Privacy accounting and quality control in the sage differentially private ML platform. Online Supplements (also available on https:\/\/arxiv.org\/abs\/1909.01502), 2019."},{"key":"e_1_3_2_1_32_1","volume-title":"Twitter meets tensorflow. https:\/\/blog.twitter.com\/engineering\/en_us\/topics\/insights\/2018\/twittertensorflow.html","author":"Leonard N.","year":"2018","unstructured":"N. Leonard and C. M. Halasz . Twitter meets tensorflow. https:\/\/blog.twitter.com\/engineering\/en_us\/topics\/insights\/2018\/twittertensorflow.html , 2018 . N. Leonard and C. M. Halasz. Twitter meets tensorflow. https:\/\/blog.twitter.com\/engineering\/en_us\/topics\/insights\/2018\/twittertensorflow.html, 2018."},{"key":"e_1_3_2_1_33_1","volume-title":"Proc. of The International Conference on Predictive Applications and APIs","author":"Li L. E.","year":"2017","unstructured":"L. E. Li , E. Chen , J. Hermann , P. Zhang , and L. Wang . Scaling machine learning as a service . In Proc. of The International Conference on Predictive Applications and APIs , 2017 . L. E. Li, E. Chen, J. Hermann, P. Zhang, and L. Wang. Scaling machine learning as a service. In Proc. of The International Conference on Predictive Applications and APIs, 2017."},{"key":"e_1_3_2_1_34_1","volume-title":"A general approach to adding differential privacy to iterative training procedures. arXiv:1812.06210","author":"McMahan H. B.","year":"2018","unstructured":"H. B. McMahan and G. Andrew . A general approach to adding differential privacy to iterative training procedures. arXiv:1812.06210 , 2018 . H. B. McMahan and G. Andrew. A general approach to adding differential privacy to iterative training procedures. arXiv:1812.06210, 2018."},{"key":"e_1_3_2_1_35_1","volume-title":"A general approach to adding differential privacy to iterative training procedures. arXiv:1812.06210","author":"McMahan H. B.","year":"2018","unstructured":"H. B. McMahan and G. Andrew . A general approach to adding differential privacy to iterative training procedures. arXiv:1812.06210 , 2018 . H. B. McMahan and G. Andrew. A general approach to adding differential privacy to iterative training procedures. arXiv:1812.06210, 2018."},{"key":"e_1_3_2_1_36_1","volume-title":"Proc. of the International Conference on Learning Representations (ICLR)","author":"McMahan H. B.","year":"2018","unstructured":"H. B. McMahan , D. Ramage , K. Talwar , and L. Zhang . Learning differentially private recurrent language models . In Proc. of the International Conference on Learning Representations (ICLR) , 2018 . H. B. McMahan, D. Ramage, K. Talwar, and L. Zhang. Learning differentially private recurrent language models. In Proc. of the International Conference on Learning Representations (ICLR), 2018."},{"key":"e_1_3_2_1_37_1","volume-title":"Proc. of the International Conference on Knowledge Discovery and Data Mining (KDD)","author":"McSherry F.","year":"2009","unstructured":"F. McSherry and I. Mironov . Differentially private recommender systems: Building privacy into the Netflix prize contenders . In Proc. of the International Conference on Knowledge Discovery and Data Mining (KDD) , 2009 . F. McSherry and I. Mironov. Differentially private recommender systems: Building privacy into the Netflix prize contenders. In Proc. of the International Conference on Knowledge Discovery and Data Mining (KDD), 2009."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559850"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213876"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2013.30"},{"key":"e_1_3_2_1_41_1","volume-title":"http:\/\/www.nyc.gov\/html\/tlc\/html\/about\/trip_record_data.shtml","author":"NYC Taxi & Limousine Commission - trip record data.","year":"2018","unstructured":"NYC Taxi & Limousine Commission - trip record data. http:\/\/www.nyc.gov\/html\/tlc\/html\/about\/trip_record_data.shtml , 2018 . NYC Taxi & Limousine Commission - trip record data. http:\/\/www.nyc.gov\/html\/tlc\/html\/about\/trip_record_data.shtml, 2018."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732296.2732300"},{"key":"e_1_3_2_1_43_1","volume-title":"On-device machine intelligence. https:\/\/ai.googleblog.com\/2017\/02\/on-device-machine-intelligence.html","author":"Ravi S.","year":"2017","unstructured":"S. Ravi . On-device machine intelligence. https:\/\/ai.googleblog.com\/2017\/02\/on-device-machine-intelligence.html , 2017 . S. Ravi. On-device machine intelligence. https:\/\/ai.googleblog.com\/2017\/02\/on-device-machine-intelligence.html, 2017."},{"key":"e_1_3_2_1_44_1","volume-title":"Proc. of the Conference on Neural Information Processing Systems (NeurIPS)","author":"Rogers R. M.","year":"2016","unstructured":"R. M. Rogers , A. Roth , J. Ullman , and S. Vadhan . Privacy odometers and filters: Pay-as-you-go composition . In Proc. of the Conference on Neural Information Processing Systems (NeurIPS) , 2016 . R. M. Rogers, A. Roth, J. Ullman, and S. Vadhan. Privacy odometers and filters: Pay-as-you-go composition. In Proc. of the Conference on Neural Information Processing Systems (NeurIPS), 2016."},{"key":"e_1_3_2_1_45_1","volume-title":"Proc. of the USENIX Symposium on Networked Systems Design and Implementation (NSDI)","author":"Roy I.","year":"2010","unstructured":"I. Roy , S. T. Setty , A. Kilzer , V. Shmatikov , and E. Witchel . Airavat: Security and privacy for MapReduce . In Proc. of the USENIX Symposium on Networked Systems Design and Implementation (NSDI) , 2010 . I. Roy, S. T. Setty, A. Kilzer, V. Shmatikov, and E. Witchel. Airavat: Security and privacy for MapReduce. In Proc. of the USENIX Symposium on Networked Systems Design and Implementation (NSDI), 2010."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"e_1_3_2_1_47_1","volume-title":"Making machine learning easy with embeddings. SysML http:\/\/www.sysml.cc\/doc\/115.pdf","author":"Shiebler D.","year":"2010","unstructured":"D. Shiebler and A. Tayal . Making machine learning easy with embeddings. SysML http:\/\/www.sysml.cc\/doc\/115.pdf , 2010 . D. Shiebler and A. Tayal. Making machine learning easy with embeddings. SysML http:\/\/www.sysml.cc\/doc\/115.pdf, 2010."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"e_1_3_2_1_49_1","author":"Smith A.","year":"2013","unstructured":"A. Smith and A. Thakurta . Differentially private model selection via stability arguments and the robustness of lasso. Journal of Machine Learning Research , 2013 . A. Smith and A. Thakurta. Differentially private model selection via stability arguments and the robustness of lasso. Journal of Machine Learning Research, 2013.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_50_1","volume-title":"Proc. of the Conference on Neural Information Processing Systems (NeurIPS)","author":"Talwar K.","year":"2015","unstructured":"K. Talwar , A. Thakurta , and L. Zhang . Nearly-optimal private LASSO . In Proc. of the Conference on Neural Information Processing Systems (NeurIPS) , 2015 . K. Talwar, A. Thakurta, and L. Zhang. Nearly-optimal private LASSO. In Proc. of the Conference on Neural Information Processing Systems (NeurIPS), 2015."},{"key":"e_1_3_2_1_51_1","volume-title":"Proc. of USENIX Security","author":"Tram\u00e8r F.","year":"2016","unstructured":"F. Tram\u00e8r , F. Zhang , A. Juels , M. K. Reiter , and T. Ristenpart . Stealing machine learning models via prediction apis . In Proc. of USENIX Security , 2016 . F. Tram\u00e8r, F. Zhang, A. Juels, M. K. Reiter, and T. Ristenpart. Stealing machine learning models via prediction apis. In Proc. of USENIX Security, 2016."},{"key":"e_1_3_2_1_52_1","volume-title":"Revisiting differentially private linear regression: optimal and adaptive prediction & estimation in unbounded domain. arXiv:1803.02596","author":"Wang Y.-X.","year":"2018","unstructured":"Y.-X. Wang . Revisiting differentially private linear regression: optimal and adaptive prediction & estimation in unbounded domain. arXiv:1803.02596 , 2018 . Y.-X. Wang. Revisiting differentially private linear regression: optimal and adaptive prediction & estimation in unbounded domain. arXiv:1803.02596, 2018."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2012.48"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00019"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196921"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.14778\/2350229.2350253"}],"event":{"name":"SOSP '19: ACM SIGOPS 27th Symposium on Operating Systems Principles","location":"Huntsville Ontario Canada","acronym":"SOSP '19","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems","USENIX Assoc USENIX Assoc"]},"container-title":["Proceedings of the 27th ACM Symposium on Operating Systems Principles"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3341301.3359639","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3341301.3359639","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3341301.3359639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:23:26Z","timestamp":1750202606000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3341301.3359639"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,27]]},"references-count":56,"alternative-id":["10.1145\/3341301.3359639","10.1145\/3341301"],"URL":"https:\/\/doi.org\/10.1145\/3341301.3359639","relation":{},"subject":[],"published":{"date-parts":[[2019,10,27]]},"assertion":[{"value":"2019-10-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}