{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T02:14:45Z","timestamp":1777601685492,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":100,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T00:00:00Z","timestamp":1655683200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NUS Early Career Research Award (NUS ECRA)","award":["NUS ECRA FY19 P16"],"award-info":[{"award-number":["NUS ECRA FY19 P16"]}]},{"name":"NUS Presidential Young Professorship research fund"},{"name":"VMWare Early Career Faculty Grant"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,21]]},"DOI":"10.1145\/3531146.3534642","type":"proceedings-article","created":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T14:27:10Z","timestamp":1655735230000},"page":"2280-2292","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":115,"title":["What Does it Mean for a Language Model to Preserve Privacy?"],"prefix":"10.1145","author":[{"given":"Hannah","family":"Brown","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore"}]},{"given":"Katherine","family":"Lee","sequence":"additional","affiliation":[{"name":"Cornell University, USA"}]},{"given":"Fatemehsadat","family":"Mireshghallah","sequence":"additional","affiliation":[{"name":"University of California, San Diego, USA"}]},{"given":"Reza","family":"Shokri","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}]},{"given":"Florian","family":"Tram\u00e8r","sequence":"additional","affiliation":[{"name":"Google Research, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2022,6,20]]},"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":"Large-scale differentially private BERT. arXiv preprint arXiv:2108.01624 abs\/2108.01624","author":"Anil Rohan","year":"2021","unstructured":"Rohan Anil, Badih Ghazi, Vineet Gupta, Ravi Kumar, and Pasin Manurangsi. 2021. Large-scale differentially private BERT. arXiv preprint arXiv:2108.01624 abs\/2108.01624 (2021)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1179601.1179608"},{"key":"e_1_3_2_1_4_1","first-page":"443","article-title":"Self-contained system for de-identifying unstructured data in healthcare records","volume":"16","author":"Austin Joseph","year":"2019","unstructured":"Joseph Austin, Shahir Kassam-Adams, Jason\u00a0A LaBonte, and Paul\u00a0J Bayless. 2019. Self-contained system for de-identifying unstructured data in healthcare records. US Patent App. 16\/255,443.","journal-title":"US Patent App."},{"key":"e_1_3_2_1_5_1","first-page":"839","article-title":"Obfuscating information related to personally identifiable information (PII)","volume":"10","author":"Balzer Andreas","year":"2020","unstructured":"Andreas Balzer, David Mowatt, and Muiris Woulfe. 2020. Obfuscating information related to personally identifiable information (PII). US Patent 10,839,104.","journal-title":"US Patent"},{"key":"e_1_3_2_1_6_1","first-page":"885","article-title":"Protecting personally identifiable information (PII) using tagging and persistence of PII","volume":"10","author":"Balzer Andreas","year":"2021","unstructured":"Andreas Balzer, David Mowatt, and Muiris Woulfe. 2021. Protecting personally identifiable information (PII) using tagging and persistence of PII. US Patent 10,885,225.","journal-title":"US Patent"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.5297715"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1075"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511813085"},{"key":"e_1_3_2_1_11_1","volume-title":"Language models are few-shot learners. arXiv preprint arXiv:2005.14165 abs\/2005.14165","author":"Brown B","year":"2020","unstructured":"Tom\u00a0B Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, 2020. Language models are few-shot learners. arXiv preprint arXiv:2005.14165 abs\/2005.14165 (2020)."},{"key":"e_1_3_2_1_12_1","volume-title":"28th {USENIX} Security Symposium ({USENIX} Security 19)","author":"Carlini Nicholas","unstructured":"Nicholas Carlini, Chang Liu, \u00dalfar Erlingsson, Jernej Kos, and Dawn Song. 2019. The secret sharer: Evaluating and testing unintended memorization in neural networks. In 28th {USENIX} Security Symposium ({USENIX} Security 19). USENIX Association, Santa Clara, CA, 267\u2013284."},{"key":"e_1_3_2_1_13_1","volume-title":"Extracting training data from large language models. arXiv preprint arXiv:2012.07805 abs\/2012.07805","author":"Carlini Nicholas","year":"2020","unstructured":"Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, 2020. Extracting training data from large language models. arXiv preprint arXiv:2012.07805 abs\/2012.07805 (2020)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-0802"},{"key":"e_1_3_2_1_15_1","volume-title":"Differentially private empirical risk minimization.Journal of Machine Learning Research 12, 3","author":"Chaudhuri Kamalika","year":"2011","unstructured":"Kamalika Chaudhuri, Claire Monteleoni, and Anand\u00a0D Sarwate. 2011. Differentially private empirical risk minimization.Journal of Machine Learning Research 12, 3 (2011), 1069\u20131109."},{"key":"e_1_3_2_1_16_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda","author":"Chen Mark","year":"2021","unstructured":"Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de\u00a0Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 abs\/2107.03374 (2021)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330723"},{"key":"e_1_3_2_1_18_1","volume-title":"Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent. In Conference on Neural Information Processing Systems (NeurIPS). NeurIPS, Online.","author":"Chourasia Rishav","year":"2021","unstructured":"Rishav Chourasia, Jiayuan Ye, and Reza Shokri. 2021. Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent. In Conference on Neural Information Processing Systems (NeurIPS). NeurIPS, Online."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocw156"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.21"},{"key":"e_1_3_2_1_21_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 abs\/1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 abs\/1810.04805 (2018)."},{"key":"e_1_3_2_1_22_1","unstructured":"Jesse Dodge Maarten Sap Ana Marasovi\u0107 William Agnew Gabriel Ilharco Dirk Groeneveld and Matt Gardner. 2021. Documenting the English Colossal Clean Crawled Corpus. ArXiv abs\/2104.08758(2021)."},{"key":"e_1_3_2_1_23_1","first-page":"891","article-title":"Management systems for personal identifying data, and methods relating thereto","volume":"10","author":"Donovan L","year":"2021","unstructured":"Jennifer\u00a0L Donovan, Gary Adler, and James Holladay. 2021. Management systems for personal identifying data, and methods relating thereto. US Patent 10,891,359.","journal-title":"US Patent"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00779-003-0253-8"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-79228-4_1"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2011.88"},{"key":"e_1_3_2_1_28_1","volume-title":"Theory of cryptography conference","author":"Dwork Cynthia","unstructured":"Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam Smith. 2006. Calibrating noise to sensitivity in private data analysis. In Theory of cryptography conference. Springer, New York, United States, 265\u2013284."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0113114"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357713.3384290"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287287"},{"key":"e_1_3_2_1_32_1","first-page":"857","article-title":"Utility-preserving text de-identification with privacy guarantees","volume":"16","author":"Gkoulalas-Divanis Aris","year":"2021","unstructured":"Aris Gkoulalas-Divanis, Paul\u00a0R Bastide, Xu Wang, and Rohit Ranchal. 2021. Utility-preserving text de-identification with privacy guarantees. US Patent App. 16\/860,857.","journal-title":"US Patent App."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1037\/xge0000498"},{"key":"e_1_3_2_1_35_1","series-title":"Syntax and Semantics","volume-title":"Speech Acts, Peter Cole and Jerry\u00a0L","author":"Grice P.","unstructured":"H.\u00a0P. Grice. 1975. Logic and Conversation. In Syntax and Semantics: Vol. 3: Speech Acts, Peter Cole and Jerry\u00a0L. Morgan (Eds.). Academic Press, New York, 41\u201358. http:\/\/www.ucl.ac.uk\/ls\/studypacks\/Grice-Logic.pdf"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-15213-0_13"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.08.002"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278777"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the International AAAI Conference on Web and Social Media 9, 1(2015)","author":"Hiruncharoenvate Chaya","year":"2015","unstructured":"Chaya Hiruncharoenvate, Zhiyuan Lin, and Eric Gilbert. 2015. Algorithmically Bypassing Censorship on Sina Weibo with Nondeterministic Homophone Substitutions. Proceedings of the International AAAI Conference on Web and Social Media 9, 1(2015), 150\u2013158. https:\/\/ojs.aaai.org\/index.php\/ICWSM\/article\/view\/14637 Number: 1."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.privatenlp-1.3"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.49"},{"key":"e_1_3_2_1_42_1","unstructured":"International Consortium of Investigative Journalists. 2016. About the Panama Papers Investigations. https:\/\/www.icij.org\/investigations\/panama-papers\/pages\/panama-papers-about-the-investigation\/."},{"key":"e_1_3_2_1_43_1","volume-title":"Delphi: Towards machine ethics and norms. arXiv preprint arXiv:2110.07574 abs\/2104.08758","author":"Jiang Liwei","year":"2021","unstructured":"Liwei Jiang, Jena\u00a0D Hwang, Chandra Bhagavatula, Ronan\u00a0Le Bras, Maxwell Forbes, Jon Borchardt, Jenny Liang, Oren Etzioni, Maarten Sap, and Yejin Choi. 2021. Delphi: Towards machine ethics and norms. arXiv preprint arXiv:2110.07574 abs\/2104.08758 (2021)."},{"key":"e_1_3_2_1_44_1","volume-title":"a freely accessible critical care database. Scientific data 3, 1","author":"Johnson EW","year":"2016","unstructured":"Alistair\u00a0EW Johnson, Tom\u00a0J Pollard, Lu Shen, H\u00a0Lehman Li-Wei, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo\u00a0Anthony Celi, and Roger\u00a0G Mark. 2016. MIMIC-III, a freely accessible critical care database. Scientific data 3, 1 (2016), 1\u20139."},{"key":"e_1_3_2_1_45_1","volume-title":"Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 abs.2001.08361","author":"Kaplan Jared","year":"2020","unstructured":"Jared Kaplan, Sam McCandlish, Tom Henighan, Tom\u00a0B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. 2020. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 abs.2001.08361 (2020)."},{"key":"e_1_3_2_1_46_1","volume-title":"International Conference on Learning Representations. ICLR, Online.","author":"Khandelwal Urvashi","year":"2019","unstructured":"Urvashi Khandelwal, Omer Levy, Dan Jurafsky, Luke Zettlemoyer, and Mike Lewis. 2019. Generalization through Memorization: Nearest Neighbor Language Models. In International Conference on Learning Representations. ICLR, Online."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3476085"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30115-8_22"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.2196\/15823"},{"key":"e_1_3_2_1_50_1","unstructured":"Latitude. 2019. Ai dungeon. https:\/\/play.aidungeon.io\/"},{"key":"e_1_3_2_1_51_1","volume-title":"Deduplicating training data makes language models better. arXiv preprint arXiv:2107.06499 abs\/2107.06499","author":"Lee Katherine","year":"2021","unstructured":"Katherine Lee, Daphne Ippolito, Andrew Nystrom, Chiyuan Zhang, Douglas Eck, Chris Callison-Burch, and Nicholas Carlini. 2021. Deduplicating training data makes language models better. arXiv preprint arXiv:2107.06499 abs\/2107.06499 (2021)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Eric Lehman Sarthak Jain Karl Pichotta Yoav Goldberg and Byron\u00a0C. Wallace. 2021. Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?arxiv:2104.07762\u00a0[cs.CL]","DOI":"10.18653\/v1\/2021.naacl-main.73"},{"key":"e_1_3_2_1_53_1","unstructured":"Alexandra\u00a0S. Levine. 2022. Suicide hotline shares data with for-profit spinoff raising ethical questions. https:\/\/www.politico.com\/news\/2022\/01\/28\/suicide-hotline-silicon-valley-privacy-debates-00002617"},{"key":"e_1_3_2_1_54_1","volume-title":"Learning with User-Level Privacy. arXiv preprint arXiv:2102.11845 abs\/2102.11845","author":"Levy Daniel","year":"2021","unstructured":"Daniel Levy, Ziteng Sun, Kareem Amin, Satyen Kale, Alex Kulesza, Mehryar Mohri, and Ananda\u00a0Theertha Suresh. 2021. Learning with User-Level Privacy. arXiv preprint arXiv:2102.11845 abs\/2102.11845 (2021)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1094"},{"key":"e_1_3_2_1_56_1","volume-title":"Large language models can be strong differentially private learners. arXiv preprint arXiv:2110.05679 abs\/2110.05679","author":"Li Xuechen","year":"2021","unstructured":"Xuechen Li, Florian Tramer, Percy Liang, and Tatsunori Hashimoto. 2021. Large language models can be strong differentially private learners. arXiv preprint arXiv:2110.05679 abs\/2110.05679 (2021)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"crossref","unstructured":"Pierre Lison Ildik\u00f3 Pil\u00e1n David S\u00e1nchez Montserrat Batet and Lilja \u00d8vrelid. 2021. Anonymisation models for text data: State of the art challenges and future directions. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). ACL Online 4188\u20134203.","DOI":"10.18653\/v1\/2021.acl-long.323"},{"key":"e_1_3_2_1_58_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 abs\/1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 abs\/1907.11692 (2019)."},{"key":"e_1_3_2_1_59_1","unstructured":"Yunhui Long Vincent Bindschaedler and Carl\u00a0A. Gunter. 2017. Towards Measuring Membership Privacy. ArXiv abs\/1712.09136(2017)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401255"},{"key":"e_1_3_2_1_61_1","volume-title":"Membership Inference on Word Embedding and Beyond. arXiv preprint arXiv:2106.11384 abs\/2106.11384","author":"Mahloujifar Saeed","year":"2021","unstructured":"Saeed Mahloujifar, Huseyin\u00a0A Inan, Melissa Chase, Esha Ghosh, and Marcello Hasegawa. 2021. Membership Inference on Word Embedding and Beyond. arXiv preprint arXiv:2106.11384 abs\/2106.11384 (2021)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.739"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1177\/1461444814543995"},{"key":"e_1_3_2_1_64_1","volume-title":"Learning differentially private language models without losing accuracy. arXiv preprint arXiv:1710.06963 abs\/1710.06963","author":"McMahan H\u00a0Brendan","year":"2017","unstructured":"H\u00a0Brendan McMahan, Daniel Ramage, Kunal Talwar, and Li Zhang. 2017. Learning differentially private language models without losing accuracy. arXiv preprint arXiv:1710.06963 abs\/1710.06963 (2017)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3012542"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-0280-0"},{"key":"e_1_3_2_1_67_1","volume-title":"Workshop on Hot Topics in Privacy Enhancing Technologies (HotPETs) 1","author":"Murakonda Sasi\u00a0Kumar","year":"2020","unstructured":"Sasi\u00a0Kumar Murakonda and Reza Shokri. 2020. ML Privacy Meter: Aiding regulatory compliance by quantifying the privacy risks of machine learning. Workshop on Hot Topics in Privacy Enhancing Technologies (HotPETs) 1 (2020)."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2008.33"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00065"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00069"},{"key":"e_1_3_2_1_71_1","volume-title":"Privacy in context","author":"Nissenbaum Helen","unstructured":"Helen Nissenbaum. 2009. Privacy in context. Stanford University Press, Stanford, CA."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-019-0215-9"},{"key":"e_1_3_2_1_73_1","volume-title":"Protected Health Information filter (Philter): accurately and securely de-identifying free-text clinical notes. NPJ digital medicine 3, 1","author":"Norgeot Beau","year":"2020","unstructured":"Beau Norgeot, Kathleen Muenzen, Thomas\u00a0A Peterson, Xuancheng Fan, Benjamin\u00a0S Glicksberg, Gundolf Schenk, Eugenia Rutenberg, Boris Oskotsky, Marina Sirota, Jinoos Yazdany, 2020. Protected Health Information filter (Philter): accurately and securely de-identifying free-text clinical notes. NPJ digital medicine 3, 1 (2020), 1\u20138."},{"key":"e_1_3_2_1_74_1","volume-title":"Specaugment: A simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779 abs\/1904.08779","author":"Park S","year":"2019","unstructured":"Daniel\u00a0S Park, William Chan, Yu Zhang, Chung-Cheng Chiu, Barret Zoph, Ekin\u00a0D Cubuk, and Quoc\u00a0V Le. 2019. Specaugment: A simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779 abs\/1904.08779 (2019)."},{"key":"e_1_3_2_1_75_1","unstructured":"Keith Porcaro. 2022. The real harm of crisis text line\u2019s data sharing. https:\/\/www.wired.com\/story\/consumer-protections-data-services-care\/"},{"key":"e_1_3_2_1_76_1","volume-title":"Language models are unsupervised multitask learners. OpenAI blog 1, 8","author":"Radford Alec","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, 2019. Language models are unsupervised multitask learners. OpenAI blog 1, 8 (2019), 9."},{"key":"e_1_3_2_1_77_1","unstructured":"Jack\u00a0W. Rae Sebastian Borgeaud Trevor Cai Katie Millican Jordan Hoffmann Francis Song John Aslanides Sarah Henderson Roman Ring Susannah Young Eliza Rutherford Tom Hennigan Jacob Menick Albin Cassirer Richard Powell George van\u00a0den Driessche Lisa\u00a0Anne Hendricks Maribeth Rauh Po-Sen Huang Amelia Glaese Johannes Welbl Sumanth Dathathri Saffron Huang Jonathan Uesato John Mellor Irina Higgins Antonia Creswell Nat McAleese Amy Wu Erich Elsen Siddhant Jayakumar Elena Buchatskaya David Budden Esme Sutherland Karen Simonyan Michela Paganini Laurent Sifre Lena Martens Xiang\u00a0Lorraine Li Adhiguna Kuncoro Aida Nematzadeh Elena Gribovskaya Domenic Donato Angeliki Lazaridou Arthur Mensch Jean-Baptiste Lespiau Maria Tsimpoukelli Nikolai Grigorev Doug Fritz Thibault Sottiaux Mantas Pajarskas Toby Pohlen Zhitao Gong Daniel Toyama Cyprien de Masson\u00a0d\u2019Autume Yujia Li Tayfun Terzi Vladimir Mikulik Igor Babuschkin Aidan Clark Diego de Las\u00a0Casas Aurelia Guy Chris Jones James Bradbury Matthew Johnson Blake Hechtman Laura Weidinger Iason Gabriel William Isaac Ed Lockhart Simon Osindero Laura Rimell Chris Dyer Oriol Vinyals Kareem Ayoub Jeff Stanway Lorrayne Bennett Demis Hassabis Koray Kavukcuoglu and Geoffrey Irving. 2021. Scaling Language Models: Methods Analysis & Insights from Training Gopher. arxiv:2112.11446\u00a0[cs.CL]"},{"key":"e_1_3_2_1_78_1","volume-title":"Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683 abs\/1910.10683","author":"Raffel Colin","year":"2019","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter\u00a0J Liu. 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683 abs\/1910.10683 (2019)."},{"key":"e_1_3_2_1_79_1","volume-title":"Training production language models without memorizing user data. arXiv preprint arXiv:2009.10031 abs\/2009.10031","author":"Ramaswamy Swaroop","year":"2020","unstructured":"Swaroop Ramaswamy, Om Thakkar, Rajiv Mathews, Galen Andrew, H\u00a0Brendan McMahan, and Fran\u00e7oise Beaufays. 2020. Training production language models without memorizing user data. arXiv preprint arXiv:2009.10031 abs\/2009.10031 (2020)."},{"key":"e_1_3_2_1_80_1","volume-title":"Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning. In 29th USENIX Security Symposium (USENIX Security 20)","author":"Salem Ahmed","year":"2020","unstructured":"Ahmed Salem, Apratim Bhattacharya, Michael Backes, Mario Fritz, and Yang Zhang. 2020. Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning. In 29th USENIX Security Symposium (USENIX Security 20). USENIX Association, Online, 1291\u20131308. https:\/\/www.usenix.org\/conference\/usenixsecurity20\/presentation\/salem"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"crossref","unstructured":"Ahmed Salem Yang Zhang Mathias Humbert Mario Fritz and Michael Backes. 2018. ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models. ArXiv abs\/1806.01246(2018).","DOI":"10.14722\/ndss.2019.23119"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1111\/josl.12069"},{"key":"e_1_3_2_1_83_1","volume-title":"Membership Inference Attacks Against NLP Classification Models. In NeurIPS 2021 Workshop Privacy in Machine Learning. NeurIPS, Online.","author":"Shejwalkar Virat","year":"2021","unstructured":"Virat Shejwalkar, Huseyin\u00a0A Inan, Amir Houmansadr, and Robert Sim. 2021. Membership Inference Attacks Against NLP Classification Models. In NeurIPS 2021 Workshop Privacy in Machine Learning. NeurIPS, Online."},{"key":"e_1_3_2_1_84_1","volume-title":"Selective Differential Privacy for Language Modeling. arXiv preprint arXiv:2108.12944 abs\/2108.12944","author":"Shi Weiyan","year":"2021","unstructured":"Weiyan Shi, Aiqi Cui, Evan Li, Ruoxi Jia, and Zhou Yu. 2021. Selective Differential Privacy for Language Modeling. arXiv preprint arXiv:2108.12944 abs\/2108.12944 (2021)."},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.2307\/40041279"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417270"},{"key":"e_1_3_2_1_88_1","unstructured":"Congzheng Song and Vitaly Shmatikov. 2018. The Natural Auditor: How To Tell If Someone Used Your Words To Train Their Model. ArXiv abs\/1811.00513(2018)."},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.5555\/6245"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1177\/09579265211013116"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.privatenlp-1.1"},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5622"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1093\/ct"},{"key":"e_1_3_2_1_94_1","volume-title":"Advances in neural information processing systems. NeurIPS","author":"Vaswani Ashish","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. NeurIPS, Long Beach, CA, 5998\u20136008."},{"key":"e_1_3_2_1_95_1","unstructured":"Laura Weidinger John Mellor Maribeth Rauh Conor Griffin Jonathan Uesato Po-Sen Huang Myra Cheng Mia Glaese Borja Balle Atoosa Kasirzadeh Zac Kenton Sasha Brown Will Hawkins Tom Stepleton Courtney Biles Abeba Birhane Julia Haas Laura Rimell Lisa\u00a0Anne Hendricks William Isaac Sean Legassick Geoffrey Irving and Iason Gabriel. 2021. Ethical and social risks of harm from Language Models. arxiv:2112.04359\u00a0[cs.CL]"},{"key":"e_1_3_2_1_96_1","first-page":"959","article-title":"Systems and methods for automatically scrubbing sensitive data","volume":"16","author":"Williams David","year":"2021","unstructured":"David Williams. 2021. Systems and methods for automatically scrubbing sensitive data. US Patent App. 16\/665,959.","journal-title":"US Patent App."},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09794-5"},{"key":"e_1_3_2_1_98_1","volume-title":"Differentially private fine-tuning of language models. arXiv preprint arXiv:2110.06500 abs\/2110.06500","author":"Yu Da","year":"2021","unstructured":"Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin\u00a0A Inan, Gautam Kamath, Janardhan Kulkarni, Yin\u00a0Tat Lee, Andre Manoel, Lukas Wutschitz, 2021. Differentially private fine-tuning of language models. arXiv preprint arXiv:2110.06500 abs\/2110.06500 (2021)."},{"key":"e_1_3_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417880"},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_101_1","volume-title":"The age of surveillance capitalism: The fight for a human future at the new frontier of power. Profile books","author":"Zuboff Shoshana","unstructured":"Shoshana Zuboff. 2019. The age of surveillance capitalism: The fight for a human future at the new frontier of power. Profile books, London."}],"event":{"name":"FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency","location":"Seoul Republic of Korea","acronym":"FAccT '22","sponsor":["ACM Association for Computing Machinery"]},"container-title":["2022 ACM Conference on Fairness Accountability and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3531146.3534642","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3531146.3534642","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:31Z","timestamp":1750188691000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3531146.3534642"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,20]]},"references-count":100,"alternative-id":["10.1145\/3531146.3534642","10.1145\/3531146"],"URL":"https:\/\/doi.org\/10.1145\/3531146.3534642","relation":{},"subject":[],"published":{"date-parts":[[2022,6,20]]},"assertion":[{"value":"2022-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}