{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:06:23Z","timestamp":1775815583824,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,1,20]],"date-time":"2020-01-20T00:00:00Z","timestamp":1579478400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,1,20]]},"DOI":"10.1145\/3336191.3371856","type":"proceedings-article","created":{"date-parts":[[2020,1,22]],"date-time":"2020-01-22T19:08:16Z","timestamp":1579720096000},"page":"178-186","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":71,"title":["Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations"],"prefix":"10.1145","author":[{"given":"Oluwaseyi","family":"Feyisetan","sequence":"first","affiliation":[{"name":"Amazon, Seattle, WA, USA"}]},{"given":"Borja","family":"Balle","sequence":"additional","affiliation":[{"name":"Amazon, Cambridge, United Kingdom"}]},{"given":"Thomas","family":"Drake","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}]},{"given":"Tom","family":"Diethe","sequence":"additional","affiliation":[{"name":"Amazon, Cambridge, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2020,1,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 24th ACM SIGKDD. ACM, 2867--2867","author":"Abowd John M","year":"2018","unstructured":"John M Abowd . 2018 . The US Census Bureau Adopts Differential Privacy . Proceedings of the 24th ACM SIGKDD. ACM, 2867--2867 . John M Abowd. 2018. The US Census Bureau Adopts Differential Privacy. Proceedings of the 24th ACM SIGKDD. ACM, 2867--2867."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2018.00026"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508859.2516735"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-015-9256-0"},{"key":"e_1_3_2_1_6_1","first-page":"667","article-title":"Privacy versus security","volume":"103","author":"Bambauer Derek E","year":"2013","unstructured":"Derek E Bambauer . 2013 . Privacy versus security . J. Crim. L. & Criminology , Vol. 103 (2013), 667 . Derek E Bambauer. 2013. Privacy versus security. J. Crim. L. & Criminology , Vol. 103 (2013), 667.","journal-title":"J. Crim. L. & Criminology"},{"key":"e_1_3_2_1_7_1","first-page":"8","article-title":"A face is exposed for AOL searcher no. 4417749","volume":"9","author":"Barbaro Michael","year":"2006","unstructured":"Michael Barbaro , Tom Zeller , and Saul Hansell . 2006 . A face is exposed for AOL searcher no. 4417749 . New York Times , Vol. 9 , 2008 (2006), 8 . Michael Barbaro, Tom Zeller, and Saul Hansell. 2006. A face is exposed for AOL searcher no. 4417749. New York Times , Vol. 9, 2008 (2006), 8.","journal-title":"New York Times"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.14778\/3055540.3055542"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"e_1_3_2_1_10_1","volume-title":"Comparative study of differentially private data synthesis methods. arXiv preprint arXiv:1602.01063","author":"McKay Bowen Claire","year":"2016","unstructured":"Claire McKay Bowen and Fang Liu . 2016. Comparative study of differentially private data synthesis methods. arXiv preprint arXiv:1602.01063 ( 2016 ). Claire McKay Bowen and Fang Liu. 2016. Comparative study of differentially private data synthesis methods. arXiv preprint arXiv:1602.01063 (2016)."},{"key":"e_1_3_2_1_11_1","unstructured":"Justin Brickell and Vitaly Shmatikov. The cost of privacy: destruction of data-mining utility in anonymized data publishing. In ACM SIGKDD .  Justin Brickell and Vitaly Shmatikov. The cost of privacy: destruction of data-mining utility in anonymized data publishing. In ACM SIGKDD ."},{"key":"e_1_3_2_1_12_1","series-title":"SIAM J. Comput. (2018)","volume-title":"Fingerprinting codes and the price of approximate differential privacy","author":"Bun Mark","unstructured":"Mark Bun , Jonathan Ullman , and Salil Vadhan . 2018. Fingerprinting codes and the price of approximate differential privacy . SIAM J. Comput. (2018) . Mark Bun, Jonathan Ullman, and Salil Vadhan. 2018. Fingerprinting codes and the price of approximate differential privacy. SIAM J. Comput. (2018)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Declan Butler. 2004. US intelligence exposed as student decodes Iraq memo. (2004).  Declan Butler. 2004. US intelligence exposed as student decodes Iraq memo. (2004).","DOI":"10.1038\/429116b"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39077-7_5"},{"key":"e_1_3_2_1_15_1","volume-title":"Cohen","author":"Coavoux Maximin","year":"2018","unstructured":"Maximin Coavoux , Shashi Narayan , and Shay B . Cohen . 2018 . Privacy-preserving Neural Representations of Text. EMNLP . Maximin Coavoux, Shashi Narayan, and Shay B. Cohen. 2018. Privacy-preserving Neural Representations of Text. EMNLP ."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Chad Cumby and Rayid Ghani. 2010. Inference control to protect sensitive information in text documents. In ACM SIGKDD WISI. ACM 5.  Chad Cumby and Rayid Ghani. 2010. Inference control to protect sensitive information in text documents. In ACM SIGKDD WISI. ACM 5.","DOI":"10.1145\/1938606.1938611"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Chad M Cumby and Rayid Ghani. 2011. A Machine Learning Based System for Semi-Automatically Redacting Documents.. In IAAI .  Chad M Cumby and Rayid Ghani. 2011. A Machine Learning Based System for Semi-Automatically Redacting Documents.. In IAAI .","DOI":"10.1609\/aaai.v25i2.18851"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/773153.773173"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1108\/14684520910985693"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1866739.1866758"},{"key":"e_1_3_2_1_21_1","volume-title":"Calibrating noise to sensitivity in private data analysis","author":"Dwork Cynthia","unstructured":"Cynthia Dwork , Frank McSherry , Kobbi Nissim , and Adam Smith . 2006. Calibrating noise to sensitivity in private data analysis . In TCC. Springer , 265--284. Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam Smith. 2006. Calibrating noise to sensitivity in private data analysis. In TCC. Springer, 265--284."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2660267.2660348"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404872"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2014.6875258"},{"key":"e_1_3_2_1_25_1","volume-title":"A fully homomorphic encryption scheme","author":"Gentry Craig","unstructured":"Craig Gentry and Dan Boneh . 2009. A fully homomorphic encryption scheme . Vol. 20 . Stanford University Stanford . Craig Gentry and Dan Boneh. 2009. A fully homomorphic encryption scheme . Vol. 20. Stanford University Stanford."},{"key":"e_1_3_2_1_26_1","volume-title":"word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method. arXiv:1402.3722","author":"Goldberg Yoav","year":"2014","unstructured":"Yoav Goldberg and Omer Levy . 2014. word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method. arXiv:1402.3722 ( 2014 ). Yoav Goldberg and Omer Levy. 2014. word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method. arXiv:1402.3722 (2014)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/1986079.1986220"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2588581"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1515\/popets-2016-0047"},{"key":"e_1_3_2_1_30_1","volume-title":"Computer Security Foundations Symposium .","author":"Hsu Justin","unstructured":"Justin Hsu , Marco Gaboardi , Andreas Haeberlen , Sanjeev Khanna , Arjun Narayan , Benjamin C Pierce , and Aaron Roth . Differential privacy : An economic method for choosing epsilon . In Computer Security Foundations Symposium . Justin Hsu, Marco Gaboardi, Andreas Haeberlen, Sanjeev Khanna, Arjun Narayan, Benjamin C Pierce, and Aaron Roth. Differential privacy: An economic method for choosing epsilon. In Computer Security Foundations Symposium ."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1137\/090756090"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30115-8_22"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Aleksandra Korolova Krishnaram Kenthapadi Nina Mishra and Alexandros Ntoulas. 2009. Releasing search queries and clicks privately. In WebConf. ACM.  Aleksandra Korolova Krishnaram Kenthapadi Nina Mishra and Alexandros Ntoulas. 2009. Releasing search queries and clicks privately. In WebConf. ACM.","DOI":"10.1145\/1526709.1526733"},{"key":"e_1_3_2_1_34_1","unstructured":"Hugo Larochelle and Stanislas Lauly. 2012. A neural autoregressive topic model. In NeurIPS. 2708--2716.  Hugo Larochelle and Stanislas Lauly. 2012. A neural autoregressive topic model. In NeurIPS. 2708--2716."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557079"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 49th Annual Meeting of the ACL . 142--150","author":"Maas Andrew L","year":"2011","unstructured":"Andrew L Maas , Raymond E Daly , Peter T Pham , Dan Huang , Andrew Y Ng , and Christopher Potts . 2011 . Learning word vectors for sentiment analysis . In Proceedings of the 49th Annual Meeting of the ACL . 142--150 . Andrew L Maas, Raymond E Daly, Peter T Pham, Dan Huang, Andrew Y Ng, and Christopher Potts. 2011. Learning word vectors for sentiment analysis. In Proceedings of the 49th Annual Meeting of the ACL . 142--150."},{"key":"e_1_3_2_1_37_1","volume-title":"Incognito: A Method for Obfuscating Web Data. In WebConf. 267--276.","author":"Masood Rahat","year":"2018","unstructured":"Rahat Masood , Dinusha Vatsalan , Muhammad Ikram , and Mohamed Ali Kaafar . 2018 . Incognito: A Method for Obfuscating Web Data. In WebConf. 267--276. Rahat Masood, Dinusha Vatsalan, Muhammad Ikram, and Mohamed Ali Kaafar. 2018. Incognito: A Method for Obfuscating Web Data. In WebConf. 267--276."},{"key":"e_1_3_2_1_38_1","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems. 3111--3119.  Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems. 3111--3119."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2008.33"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2009.22"},{"key":"e_1_3_2_1_41_1","unstructured":"Vijay Pandurangan. 2014. On taxis and rainbows: Lessons from NYC's improperly anonymized taxi logs. (2014).  Vijay Pandurangan. 2014. On taxis and rainbows: Lessons from NYC's improperly anonymized taxi logs. (2014)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920918"},{"key":"e_1_3_2_1_43_1","first-page":"1","article-title":"A picture of search","volume":"152","author":"Pass Greg","year":"2006","unstructured":"Greg Pass , Abdur Chowdhury , and Cayley Torgeson . 2006 . A picture of search .. In InfoScale , Vol. 152. 1 . Greg Pass, Abdur Chowdhury, and Cayley Torgeson. 2006. A picture of search.. In InfoScale, Vol. 152. 1.","journal-title":"InfoScale"},{"key":"e_1_3_2_1_44_1","volume-title":"Glove: Global vectors for word representation. In EMNLP. 1532--1543.","author":"Pennington Jeffrey","year":"2014","unstructured":"Jeffrey Pennington , Richard Socher , and Christopher Manning . 2014 . Glove: Global vectors for word representation. In EMNLP. 1532--1543. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word representation. In EMNLP. 1532--1543."},{"key":"e_1_3_2_1_45_1","volume-title":"Lionel Brunie, and Harald Kosch.","author":"Petit Albin","year":"2015","unstructured":"Albin Petit , Thomas Cerqueus , Sonia Ben Mokhtar , Lionel Brunie, and Harald Kosch. 2015 . PEAS : Private, efficient and accurate web search. In Trustcom. IEEE. Albin Petit, Thomas Cerqueus, Sonia Ben Mokhtar, Lionel Brunie, and Harald Kosch. 2015. PEAS: Private, efficient and accurate web search. In Trustcom. IEEE."},{"key":"e_1_3_2_1_47_1","first-page":"148","article-title":"C-sanitized: A privacy model for document redaction and sanitization","volume":"67","author":"S\u00e1nchez David","year":"2016","unstructured":"David S\u00e1nchez and Montserrat Batet . 2016 . C-sanitized: A privacy model for document redaction and sanitization . JAIST , Vol. 67 , 1 (2016), 148 -- 163 . David S\u00e1nchez and Montserrat Batet. 2016. C-sanitized: A privacy model for document redaction and sanitization. JAIST , Vol. 67, 1 (2016), 148--163.","journal-title":"JAIST"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2012.06.025"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"crossref","unstructured":"Tobias Schnabel Igor Labutov David Mimno and Thorsten Joachims. 2015. Evaluation methods for unsupervised word embeddings. In EMNLP. 298--307.  Tobias Schnabel Igor Labutov David Mimno and Thorsten Joachims. 2015. Evaluation methods for unsupervised word embeddings. In EMNLP. 298--307.","DOI":"10.18653\/v1\/D15-1036"},{"key":"e_1_3_2_1_50_1","volume-title":"Proceedings of the 22nd ACM SIGSAC CCS. ACM, 1310--1321","author":"Shokri Reza","year":"2015","unstructured":"Reza Shokri and Vitaly Shmatikov . 2015 . Privacy-preserving deep learning . In Proceedings of the 22nd ACM SIGSAC CCS. ACM, 1310--1321 . Reza Shokri and Vitaly Shmatikov. 2015. Privacy-preserving deep learning. In Proceedings of the 22nd ACM SIGSAC CCS. ACM, 1310--1321."},{"key":"e_1_3_2_1_51_1","volume-title":"Membership inference attacks against machine learning models","author":"Shokri Reza","unstructured":"Reza Shokri , Marco Stronati , Congzheng Song , and Vitaly Shmatikov . 2017. Membership inference attacks against machine learning models . In SP. IEEE. Reza Shokri, Marco Stronati, Congzheng Song, and Vitaly Shmatikov. 2017. Membership inference attacks against machine learning models. In SP. IEEE."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Congzheng Song and Vitaly Shmatikov. 2019. Auditing Data Provenance in Text-Generation Models. In ACM SIGKDD . https:\/\/arxiv.org\/pdf\/1811.00513.pdf  Congzheng Song and Vitaly Shmatikov. 2019. Auditing Data Provenance in Text-Generation Models. In ACM SIGKDD . https:\/\/arxiv.org\/pdf\/1811.00513.pdf","DOI":"10.1145\/3292500.3330885"},{"key":"e_1_3_2_1_53_1","volume-title":"LSTM-based deep learning models for non-factoid answer selection. arXiv:1511.04108","author":"Tan Ming","year":"2015","unstructured":"Ming Tan , Cicero dos Santos , Bing Xiang , and Bowen Zhou . 2015. LSTM-based deep learning models for non-factoid answer selection. arXiv:1511.04108 ( 2015 ). Ming Tan, Cicero dos Santos, Bing Xiang, and Bowen Zhou. 2015. LSTM-based deep learning models for non-factoid answer selection. arXiv:1511.04108 (2015)."},{"key":"e_1_3_2_1_54_1","first-page":"594","article-title":"Learning new words. (2017)","volume":"9","author":"Thakurta Abhradeep Guha","year":"2017","unstructured":"Abhradeep Guha Thakurta , Andrew H Vyrros , Umesh S Vaishampayan , Gaurav Kapoor , Julien Freudiger , Vivek Rangarajan Sridhar , and Doug Davidson . 2017 . Learning new words. (2017) . US Patent 9 , 594 ,741. Abhradeep Guha Thakurta, Andrew H Vyrros, Umesh S Vaishampayan, Gaurav Kapoor, Julien Freudiger, Vivek Rangarajan Sridhar, and Doug Davidson. 2017. Learning new words. (2017). US Patent 9,594,741.","journal-title":"US Patent"},{"key":"e_1_3_2_1_55_1","volume-title":"September","volume":"15","author":"Tockar Anthony","year":"2014","unstructured":"Anthony Tockar . 2014 . Riding with the stars: Passenger privacy in the NYC taxicab dataset. Neustar Research , September , Vol. 15 (2014). Anthony Tockar. 2014. Riding with the stars: Passenger privacy in the NYC taxicab dataset. Neustar Research, September , Vol. 15 (2014)."},{"key":"e_1_3_2_1_56_1","volume-title":"Privacy Risks with Facebook's PII-based Targeting: Auditing a Data Broker's Advertising Interface","author":"Venkatadri Giridhari","unstructured":"Giridhari Venkatadri , Athanasios Andreou , Yabing Liu , Alan Mislove , Krishna Gummadi , Patrick Loiseau , and Oana Goga . 2018. Privacy Risks with Facebook's PII-based Targeting: Auditing a Data Broker's Advertising Interface . In IEEE SP . Giridhari Venkatadri, Athanasios Andreou, Yabing Liu, Alan Mislove, Krishna Gummadi, Patrick Loiseau, and Oana Goga. 2018. Privacy Risks with Facebook's PII-based Targeting: Auditing a Data Broker's Advertising Interface. In IEEE SP ."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3168389"},{"key":"e_1_3_2_1_58_1","unstructured":"Tianhao Wang Jeremiah Blocki Ninghui Li and Somesh Jha. 2017. Locally differentially private protocols for frequency estimation. In USENIX . 729--745.  Tianhao Wang Jeremiah Blocki Ninghui Li and Somesh Jha. 2017. Locally differentially private protocols for frequency estimation. In USENIX . 729--745."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210008"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3064047"}],"event":{"name":"WSDM '20: The Thirteenth ACM International Conference on Web Search and Data Mining","location":"Houston TX USA","acronym":"WSDM '20","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 13th International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3336191.3371856","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3336191.3371856","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:23:14Z","timestamp":1750202594000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3336191.3371856"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,20]]},"references-count":59,"alternative-id":["10.1145\/3336191.3371856","10.1145\/3336191"],"URL":"https:\/\/doi.org\/10.1145\/3336191.3371856","relation":{},"subject":[],"published":{"date-parts":[[2020,1,20]]},"assertion":[{"value":"2020-01-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}