{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T11:03:03Z","timestamp":1781002983776,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":127,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62272410"],"award-info":[{"award-number":["62272410"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3772318.3791809","type":"proceedings-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:12:21Z","timestamp":1776053541000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["The Privacy Paradox of LLMs: User Perceptions and the Reality of PII Leakage"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8731-5587","authenticated-orcid":false,"given":"Shuai","family":"Cheng","sequence":"first","affiliation":[{"name":"Zhejiang University, HangZhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0353-3879","authenticated-orcid":false,"given":"Haitao","family":"Xu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0442-6585","authenticated-orcid":false,"given":"Shu","family":"Meng","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7483-5252","authenticated-orcid":false,"given":"Shuai","family":"Hao","sequence":"additional","affiliation":[{"name":"Old Dominion University, Norfolk, Virginia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6095-4768","authenticated-orcid":false,"given":"Chuan","family":"Yue","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Colorado School of Mines, Golden, Colorado, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5056-0351","authenticated-orcid":false,"given":"Zhao","family":"Li","sequence":"additional","affiliation":[{"name":"Hangzhou Yugu Technology, Hangzhou, China and Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"[n. d.]. Serper. Serper. https:\/\/serper.dev\/."},{"key":"e_1_3_3_2_3_2","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia\u00a0Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et\u00a0al. 2023. Gpt-4 technical report. arXiv:https:\/\/arXiv.org\/abs\/2303.08774 (2023)."},{"key":"e_1_3_3_2_4_2","unstructured":"Atilla Akkus Mingjie Li Junjie Chu Michael Backes Yang Zhang and Sinem Sav. 2024. Generated data with fake privacy: Hidden dangers of fine-tuning large language models on generated data. arXiv:https:\/\/arXiv.org\/abs\/2409.11423 (2024)."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Daniel\u00a0Alexander Alber Zihao Yang Anton Alyakin Eunice Yang Sumedha Rai Aly\u00a0A Valliani Jeff Zhang Gabriel\u00a0R Rosenbaum Ashley\u00a0K Amend-Thomas David\u00a0B Kurland et\u00a0al. 2025. Medical large language models are vulnerable to data-poisoning attacks. Nature Medicine 31 2 (2025) 618\u2013626.","DOI":"10.1038\/s41591-024-03445-1"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP61157.2025.00241"},{"key":"e_1_3_3_2_7_2","unstructured":"Anthropic. 2024. Anthropic Privacy Policy. https:\/\/www.anthropic.com\/legal\/privacy."},{"key":"e_1_3_3_2_8_2","unstructured":"Anthropic. 2025. Claude Opus 4 and Sonnet 4 Model Card. https:\/\/www.anthropic.com\/transparency. Accessed: 2025-09-08."},{"key":"e_1_3_3_2_9_2","unstructured":"Tomer Ashuach Martin Tutek and Yonatan Belinkov. 2024. REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space. arXiv:https:\/\/arXiv.org\/abs\/2406.09325 (2024)."},{"key":"e_1_3_3_2_10_2","unstructured":"Yang Bai Ge Pei Jindong Gu Yong Yang and Xingjun Ma. 2024. Special characters attack: Toward scalable training data extraction from large language models. arXiv:https:\/\/arXiv.org\/abs\/2405.05990 (2024)."},{"key":"e_1_3_3_2_11_2","unstructured":"Evan Bailyn. 2025. ChatGPT Usage Statistics. First Page Sage Blog. https:\/\/firstpagesage.com\/seo-blog\/chatgpt-usage-statistics"},{"key":"e_1_3_3_2_12_2","unstructured":"Stella Biderman Usvsn Prashanth Lintang Sutawika Hailey Schoelkopf Quentin Anthony Shivanshu Purohit and Edward Raff. 2024. Emergent and predictable memorization in large language models. NeurIPS 36 (2024)."},{"key":"e_1_3_3_2_13_2","first-page":"2397","volume-title":"International Conference on Machine Learning","author":"Biderman Stella","year":"2023","unstructured":"Stella Biderman, Hailey Schoelkopf, Quentin\u00a0Gregory Anthony, Herbie Bradley, Kyle O\u2019Brien, Eric Hallahan, Mohammad\u00a0Aflah Khan, Shivanshu Purohit, USVSN\u00a0Sai Prashanth, Edward Raff, et\u00a0al. 2023. Pythia: A suite for analyzing large language models across training and scaling. In International Conference on Machine Learning. PMLR, 2397\u20132430."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Sid Black Stella Biderman Eric Hallahan Quentin Anthony Leo Gao Laurence Golding Horace He Connor Leahy Kyle McDonell Jason Phang et\u00a0al. 2022. Gpt-neox-20b: An open-source autoregressive language model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.06745 (2022).","DOI":"10.18653\/v1\/2022.bigscience-1.9"},{"key":"e_1_3_3_2_15_2","unstructured":"Sid Black Leo Gao Phil Wang Connor Leahy and Stella Biderman. 2021. Gpt-neo: Large scale autoregressive language modeling with mesh-tensorflow. If you use this software please cite it using these metadata 58 2 (2021)."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Nadine Bol Tobias Dienlin Sanne Kruikemeier Marijn Sax Sophie\u00a0C Boerman Joanna Strycharz Natali Helberger and Claes\u00a0H De\u00a0Vreese. 2018. Understanding the effects of personalization as a privacy calculus: Analyzing self-disclosure across health news and commerce contexts. Journal of Computer-Mediated Communication 23 6 (2018) 370\u2013388.","DOI":"10.1093\/jcmc\/zmy020"},{"key":"e_1_3_3_2_17_2","unstructured":"Jaydeep Borkar. 2023. What can we learn from Data Leakage and Unlearning for Law? arXiv:https:\/\/arXiv.org\/abs\/2307.10476 (2023)."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Jaydeep Borkar Matthew Jagielski Katherine Lee Niloofar Mireshghallah David\u00a0A Smith and Christopher\u00a0A Choquette-Choo. 2025. Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.15680 (2025).","DOI":"10.18653\/v1\/2025.findings-acl.959"},{"key":"e_1_3_3_2_19_2","volume-title":"Meta AI was leaking chatbot prompts and answers to unauthorized users","author":"Bouman Amber","year":"2025","unstructured":"Amber Bouman. 2025. Meta AI was leaking chatbot prompts and answers to unauthorized users. https:\/\/www.tomsguide.com\/computing\/online-security\/meta-ai-was-leaking-chatbot-prompts-and-answers-to-unauthorized-users Published: 17 July 2025; Accessed: 2025-09-10."},{"key":"e_1_3_3_2_20_2","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. NeurIPS 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_2_21_2","first-page":"267","volume-title":"USENIX Security","author":"Carlini Nicholas","year":"2019","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 USENIX Security. 267\u2013284."},{"key":"e_1_3_3_2_22_2","first-page":"2633","volume-title":"USENIX Security","author":"Carlini Nicholas","year":"2021","unstructured":"Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, et\u00a0al. 2021. Extracting training data from large language models. In USENIX Security. 2633\u20132650."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Jay\u00a0P Carlson William\u00a0O Bearden and David\u00a0M Hardesty. 2007. Influences on what consumers know and what they think they know regarding marketer pricing tactics. Psychology & Marketing 24 2 (2007) 117\u2013142.","DOI":"10.1002\/mar.20155"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.3386\/w34255"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Guangxuan Chen Qiang Liu Guangxiao Chen and Anan Huang. 2025. Exploring illicit personal information trading behind telecom fraud in China. Humanities and Social Sciences Communications 12 1 (2025) 1\u201311.","DOI":"10.1057\/s41599-025-05972-9"},{"key":"e_1_3_3_2_26_2","unstructured":"Ruizhe Chen Tianxiang Hu Yang Feng and Zuozhu Liu. 2024. Learnable Privacy Neurons Localization in Language Models. arXiv:https:\/\/arXiv.org\/abs\/2405.10989 (2024)."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3690325"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/1156"},{"key":"e_1_3_3_2_29_2","first-page":"8155","volume-title":"34th USENIX Security Symposium (USENIX Security 25)","author":"Cheng Shuai","year":"2025","unstructured":"Shuai Cheng, Shu Meng, Haitao Xu, Haoran Zhang, Shuai Hao, Chuan Yue, Wenrui Ma, Meng Han, Fan Zhang, and Zhao Li. 2025. Effective { PII} Extraction from { LLMs} through Augmented { Few-Shot} Learning. In 34th USENIX Security Symposium (USENIX Security 25). 8155\u20138173."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"crossref","unstructured":"Christy\u00a0M Cheung and Matthew\u00a0K Lee. 2001. Trust in internet shopping: instrument development and validation through classical and modern approaches. Journal of Global Information Management (JGIM) 9 3 (2001) 23\u201335.","DOI":"10.4018\/jgim.2001070103"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Hanbyul Choi Jonghwa Park and Yoonhyuk Jung. 2018. The role of privacy fatigue in online privacy behavior. Computers in Human Behavior 81 (2018) 42\u201351.","DOI":"10.1016\/j.chb.2017.12.001"},{"key":"e_1_3_3_2_32_2","unstructured":"Chun\u00a0Jie Chong Chenxi Hou Zhihao Yao and Seyed Mohammadjavad\u00a0Seyed Talebi. 2024. Casper: Prompt Sanitization for Protecting User Privacy in Web-Based Large Language Models. arXiv:https:\/\/arXiv.org\/abs\/2408.07004 (2024)."},{"key":"e_1_3_3_2_33_2","unstructured":"Common Crawl. 2025. Common Crawl. https:\/\/commoncrawl.org."},{"key":"e_1_3_3_2_34_2","unstructured":"Credamo. 2025. Credamo \u2013 Intelligent Research Platform. https:\/\/www.credamo.cc\/. An online platform offering services such as questionnaire design sample recruitment and data analytics."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Mary\u00a0J Culnan and Pamela\u00a0K Armstrong. 1999. Information privacy concerns procedural fairness and impersonal trust: An empirical investigation. Organization science 10 1 (1999) 104\u2013115.","DOI":"10.1287\/orsc.10.1.104"},{"key":"e_1_3_3_2_36_2","unstructured":"Ajinkya Deshmukh Saumya Banthia and Anantha Sharma. 2023. Life of PII\u2013A PII Obfuscation Transformer. arXiv:https:\/\/arXiv.org\/abs\/2305.09550 (2023)."},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Tamara Dinev and Paul Hart. 2006. An extended privacy calculus model for e-commerce transactions. Information systems research 17 1 (2006) 61\u201380.","DOI":"10.1287\/isre.1060.0080"},{"key":"e_1_3_3_2_38_2","unstructured":"Fabio Duarte. 2025. Number of ChatGPT Users (July 2025). https:\/\/explodingtopics.com\/blog\/chatgpt-users."},{"key":"e_1_3_3_2_39_2","unstructured":"Md\u00a0Meftahul Ferdaus Mahdi Abdelguerfi Elias Ioup Kendall\u00a0N Niles Ken Pathak and Steven Sloan. 2024. Towards trustworthy ai: A review of ethical and robust large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.13934 (2024)."},{"key":"e_1_3_3_2_40_2","volume-title":"Statistical methods for rates and proportions","author":"Fleiss Joseph\u00a0L","year":"2013","unstructured":"Joseph\u00a0L Fleiss, Bruce Levin, and Myunghee\u00a0Cho Paik. 2013. Statistical methods for rates and proportions. john wiley & sons."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Donna\u00a0L Floyd Steven Prentice-Dunn and Ronald\u00a0W Rogers. 2000. A meta-analysis of research on protection motivation theory. Journal of applied social psychology 30 2 (2000) 407\u2013429.","DOI":"10.1111\/j.1559-1816.2000.tb02323.x"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3719816"},{"key":"e_1_3_3_2_43_2","unstructured":"Ahmed Frikha Nassim Walha Krishna\u00a0Kanth Nakka Ricardo Mendes Xue Jiang and Xuebing Zhou. 2024. IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization. arXiv:https:\/\/arXiv.org\/abs\/2407.02956 (2024)."},{"key":"e_1_3_3_2_44_2","unstructured":"Leo Gao Stella Biderman Sid Black Laurence Golding Travis Hoppe Charles Foster Jason Phang Horace He Anish Thite Noa Nabeshima et\u00a0al. 2020. The pile: An 800gb dataset of diverse text for language modeling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2101.00027 (2020)."},{"key":"e_1_3_3_2_45_2","unstructured":"Leo Gao Sid Black Stella Biderman Laurence Golding Travis Hoppe Charles Foster Jason Phang Horace He Anish Thite Noa Nabeshima Shawn Presser and Connor Leahy. 2020. OpenWebText2: An Improved Open-source WebText Corpus. https:\/\/github.com\/EleutherAI\/openwebtext2. EleutherAI Project."},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"crossref","unstructured":"Nina Gerber Paul Gerber and Melanie Volkamer. 2018. Explaining the privacy paradox: A systematic review of literature investigating privacy attitude and behavior. Computers & security 77 (2018) 226\u2013261.","DOI":"10.1016\/j.cose.2018.04.002"},{"key":"e_1_3_3_2_47_2","unstructured":"Aaron Gokaslan and Vanya Cohen. 2019. OpenWebText Corpus: An Open-source Replication of the WebText Dataset. https:\/\/skylion007.github.io\/OpenWebTextCorpus\/. Accessed: 2025-09-08."},{"key":"e_1_3_3_2_48_2","unstructured":"Ece Gumusel Kyrie\u00a0Zhixuan Zhou and Madelyn\u00a0Rose Sanfilippo. 2024. User privacy harms and risks in conversational ai: A proposed framework. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.09716 (2024)."},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"crossref","unstructured":"Anil Gurung Xin Luo and Qinyu Liao. 2009. Consumer motivations in taking action against spyware: An empirical investigation. Information Management & Computer Security 17 3 (2009) 276\u2013289.","DOI":"10.1108\/09685220910978112"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"crossref","unstructured":"Christian\u00a0Pieter Hoffmann Christoph Lutz and Giulia Ranzini. 2016. Privacy cynicism: A new approach to the privacy paradox. Cyberpsychology: Journal of Psychosocial Research on Cyberspace 10 4 (2016).","DOI":"10.5817\/CP2016-4-7"},{"key":"e_1_3_3_2_51_2","first-page":"1178","volume-title":"EMNLP","author":"Hoory Shlomo","year":"2021","unstructured":"Shlomo Hoory, Amir Feder, Avichai Tendler, Sofia Erell, Alon Peled-Cohen, Itay Laish, Hootan Nakhost, Uri Stemmer, et\u00a0al. 2021. Learning and evaluating a differentially private pre-trained language model. In EMNLP. 1178\u20131189."},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.148"},{"key":"e_1_3_3_2_53_2","unstructured":"Aaron Hurst Adam Lerer Adam\u00a0P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et\u00a0al. 2024. Gpt-4o system card. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.21276 (2024)."},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"crossref","unstructured":"Princely Ifinedo. 2012. Understanding information systems security policy compliance: An integration of the theory of planned behavior and the protection motivation theory. Computers & Security 31 1 (2012) 83\u201395.","DOI":"10.1016\/j.cose.2011.10.007"},{"key":"e_1_3_3_2_55_2","unstructured":"Joel Jang Dongkeun Yoon Sohee Yang Sungmin Cha Moontae Lee Lajanugen Logeswaran and Minjoon Seo. 2022. Knowledge unlearning for mitigating privacy risks in language models. arXiv:https:\/\/arXiv.org\/abs\/2210.01504 (2022)."},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713452"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"crossref","unstructured":"Allen\u00a0C Johnston and Merrill Warkentin. 2010. Fear appeals and information security behaviors: An empirical study. MIS quarterly (2010) 549\u2013566.","DOI":"10.2307\/25750691"},{"key":"e_1_3_3_2_58_2","first-page":"10697","volume-title":"International Conference on Machine Learning","author":"Kandpal Nikhil","year":"2022","unstructured":"Nikhil Kandpal, Eric Wallace, and Colin Raffel. 2022. Deduplicating training data mitigates privacy risks in language models. In International Conference on Machine Learning. PMLR, 10697\u201310707."},{"key":"e_1_3_3_2_59_2","unstructured":"Siwon Kim Sangdoo Yun Hwaran Lee Martin Gubri Sungroh Yoon and Seong\u00a0Joon Oh. 2024. Propile: Probing privacy leakage in large language models. NeurIPS 36 (2024)."},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30115-8_22"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"crossref","unstructured":"Spyros Kokolakis. 2017. Privacy attitudes and privacy behaviour: A review of current research on the privacy paradox phenomenon. Computers & security 64 (2017) 122\u2013134.","DOI":"10.1016\/j.cose.2015.07.002"},{"key":"e_1_3_3_2_62_2","first-page":"6007","volume-title":"34th USENIX Security Symposium (USENIX Security 25)","author":"Kwesi Jabari","year":"2025","unstructured":"Jabari Kwesi, Jiaxun Cao, Riya Manchanda, and Pardis Emami-Naeini. 2025. Exploring User Security and Privacy Attitudes and Concerns Toward the Use of { General-Purpose}{ LLM} Chatbots for Mental Health. In 34th USENIX Security Symposium (USENIX Security 25). 6007\u20136024."},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"crossref","unstructured":"Matthew\u00a0KO Lee and Efraim Turban. 2001. A trust model for consumer internet shopping. International Journal of electronic commerce 6 1 (2001) 75\u201391.","DOI":"10.1080\/10864415.2001.11044227"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/2501604.2501611"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.272"},{"key":"e_1_3_3_2_66_2","unstructured":"Huigang Liang Yajiong\u00a0Lucky Xue et\u00a0al. 2010. Understanding security behaviors in personal computer usage: A threat avoidance perspective. Journal of the association for information systems 11 7 (2010) 1."},{"key":"e_1_3_3_2_67_2","unstructured":"Fangyu Lin Laura Brandimarte Sue Brown and Hsinchun Chen. 2024. Examining the Effect of Personalized PII Exposure Alerts on Individuals\u2019 Privacy Protection Motivation. (2024)."},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP61157.2025.00092"},{"key":"e_1_3_3_2_69_2","unstructured":"LMArena Team. 2025. Leaderboard Changelog: notable updates to model leaderboards. https:\/\/news.lmarena.ai\/leaderboard-changelog\/."},{"key":"e_1_3_3_2_70_2","unstructured":"Shuai Lu Daya Guo Shuo Ren Junjie Huang Alexey Svyatkovskiy Ambrosio Blanco Colin Clement Dawn Drain Daxin Jiang Duyu Tang et\u00a0al. 2021. Codexglue: A machine learning benchmark dataset for code understanding and generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2102.04664 (2021)."},{"key":"e_1_3_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179300"},{"key":"e_1_3_3_2_72_2","unstructured":"Lumivero. 2025. NVivo: Leading Qualitative Data Analysis Software. Lumivero product page. https:\/\/lumivero.com\/products\/nvivo\/"},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713540"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714074"},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412762"},{"key":"e_1_3_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2207758"},{"key":"e_1_3_3_2_77_2","doi-asserted-by":"crossref","unstructured":"Erika McCallister Timothy Grance and Karen\u00a0A Scarfone. 2010. Sp 800-122. guide to protecting the confidentiality of personally identifiable information (pii).","DOI":"10.6028\/NIST.SP.800-122"},{"key":"e_1_3_3_2_78_2","unstructured":"Kevin Meng Arnab\u00a0Sen Sharma Alex Andonian Yonatan Belinkov and David Bau. 2022. Mass-editing memory in a transformer. arXiv:https:\/\/arXiv.org\/abs\/2210.07229 (2022)."},{"key":"e_1_3_3_2_79_2","unstructured":"Stephen Merity Caiming Xiong James Bradbury and Richard Socher. 2016. Pointer sentinel mixture models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1609.07843 (2016)."},{"key":"e_1_3_3_2_80_2","doi-asserted-by":"crossref","unstructured":"Sarah Milne Paschal Sheeran and Sheina Orbell. 2000. Prediction and intervention in health-related behavior: A meta-analytic review of protection motivation theory. Journal of applied social psychology 30 1 (2000) 106\u2013143.","DOI":"10.1111\/j.1559-1816.2000.tb02308.x"},{"key":"e_1_3_3_2_81_2","unstructured":"Ariffud Muhammad. 2025. LLM Statistics 2025: Comprehensive Insights Into Market Trends and Integration. Hostinger Tutorials. https:\/\/www.hostinger.com\/tutorials\/llm-statistics\/"},{"key":"e_1_3_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.privatenlp-1.7"},{"key":"e_1_3_3_2_83_2","unstructured":"Milad Nasr Nicholas Carlini Jonathan Hayase Matthew Jagielski A\u00a0Feder Cooper Daphne Ippolito Christopher\u00a0A Choquette-Choo Eric Wallace Florian Tram\u00e8r and Katherine Lee. 2023. Scalable extraction of training data from (production) language models. arXiv:https:\/\/arXiv.org\/abs\/2311.17035 (2023)."},{"key":"e_1_3_3_2_84_2","volume-title":"Hundreds of LLM Servers Expose Corporate, Health & Other Online Data","author":"Nelson Nate","year":"2024","unstructured":"Nate Nelson. 2024. Hundreds of LLM Servers Expose Corporate, Health & Other Online Data. https:\/\/www.darkreading.com\/application-security\/hundreds-of-llm-servers-expose-corporate-health-and-other-online-data Published: 28 August 2024; Accessed: 2025-09-10."},{"key":"e_1_3_3_2_85_2","volume-title":"USENIX Security","author":"Niu Liang","year":"2023","unstructured":"Liang Niu, Shujaat Mirza, Zayd Maradni, and Christina P\u00f6pper. 2023. { CodexLeaks} : Privacy leaks from code generation language models in { GitHub} copilot. In USENIX Security."},{"key":"e_1_3_3_2_86_2","unstructured":"OpenAI. 2023. OpenAI Privacy Policy. https:\/\/openai.com\/policies\/privacy-policy."},{"key":"e_1_3_3_2_87_2","unstructured":"OpenAI. 2025. Content Moderation \u2013 OpenAI Platform. https:\/\/platform.openai.com\/docs\/guides\/moderation."},{"key":"e_1_3_3_2_88_2","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et\u00a0al. 2022. Training language models to follow instructions with human feedback. NeurIPS (2022)."},{"key":"e_1_3_3_2_89_2","volume-title":"ICLR","author":"Panda Ashwinee","year":"2024","unstructured":"Ashwinee Panda, Christopher\u00a0A. Choquette-Choo, Zhengming Zhang, Yaoqing Yang, and Prateek Mittal. 2024. Teach llms to phish: Stealing private information from language models. In ICLR. https:\/\/openreview.net\/forum?id=qo21ZlfNu6"},{"key":"e_1_3_3_2_90_2","doi-asserted-by":"crossref","unstructured":"Emmanouil Papagiannidis Patrick Mikalef and Kieran Conboy. 2025. Responsible artificial intelligence governance: A review and research framework. The Journal of Strategic Information Systems 34 2 (2025) 101885.","DOI":"10.1016\/j.jsis.2024.101885"},{"key":"e_1_3_3_2_91_2","unstructured":"Guilherme Penedo Quentin Malartic Daniel Hesslow Ruxandra Cojocaru Alessandro Cappelli Hamza Alobeidli Baptiste Pannier Ebtesam Almazrouei and Julien Launay. 2023. The RefinedWeb dataset for Falcon LLM: outperforming curated corpora with web data and web data only. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.01116 (2023)."},{"key":"e_1_3_3_2_92_2","volume-title":"Leaking Minds: How Your Data Could Slip Through AI Chatbots","author":"Pigassou Jeanne","year":"2025","unstructured":"Jeanne Pigassou and Rayan\u00a0Ben Taleb. 2025. Leaking Minds: How Your Data Could Slip Through AI Chatbots. https:\/\/www.riskinsight-wavestone.com\/en\/2025\/05\/leaking-minds-how-your-data-could-slip-through-ai-chatbots\/ Accessed: 2025-09-10."},{"key":"e_1_3_3_2_93_2","unstructured":"Jiantao Qiu Haijun Lv Zhenjiang Jin Rui Wang Wenchang Ning Jia Yu ChaoBin Zhang Zhenxiang Li Pei Chu Yuan Qu et\u00a0al. 2024. Wanjuan-cc: A safe and high-quality open-sourced english webtext dataset. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.19282 (2024)."},{"key":"e_1_3_3_2_94_2","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et\u00a0al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_3_2_95_2","unstructured":"Colin Raffel Noam Shazeer Adam Roberts Katherine Lee Sharan Narang Michael Matena Yanqi Zhou Wei Li and Peter\u00a0J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research 21 140 (2020) 1\u201367."},{"key":"e_1_3_3_2_96_2","doi-asserted-by":"crossref","unstructured":"Puthankurissi\u00a0S Raju Subhash\u00a0C Lonial and W\u00a0Glynn Mangold. 1995. Differential effects of subjective knowledge objective knowledge and usage experience on decision making: An exploratory investigation. Journal of consumer psychology 4 2 (1995) 153\u2013180.","DOI":"10.1207\/s15327663jcp0402_04"},{"key":"e_1_3_3_2_97_2","doi-asserted-by":"crossref","unstructured":"Md\u00a0Rafi\u00a0Ur Rashid Jing Liu Toshiaki Koike-Akino Ye Wang and Shagufta Mehnaz. 2025. Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage. Proceedings of the AAAI Conference on Artificial Intelligence 39 (2025).","DOI":"10.1609\/aaai.v39i19.34218"},{"key":"e_1_3_3_2_98_2","doi-asserted-by":"crossref","unstructured":"Caitlin\u00a0M Rivers and Bryan\u00a0L Lewis. 2014. Ethical research standards in a world of big data. F1000Research 3 (2014) 38.","DOI":"10.12688\/f1000research.3-38.v2"},{"key":"e_1_3_3_2_99_2","doi-asserted-by":"crossref","unstructured":"Ronald\u00a0W Rogers. 1975. A protection motivation theory of fear appeals and attitude change1. The journal of psychology 91 1 (1975) 93\u2013114.","DOI":"10.1080\/00223980.1975.9915803"},{"key":"e_1_3_3_2_100_2","unstructured":"Ronald\u00a0W Rogers. 1983. Cognitive and physiological processes in fear appeals and attitude change: A revised theory of protection motivation. Social psychology: A source book (1983) 153\u2013176."},{"key":"e_1_3_3_2_101_2","unstructured":"Sruly Rosenblat Tim O\u2019Reilly and Ilan Strauss. 2025. Beyond Public Access in LLM Pre-Training Data. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.00020 (2025)."},{"key":"e_1_3_3_2_102_2","unstructured":"Wilmar\u00a0B Schaufeli. 1996. Maslach burnout inventory-general survey (MBI-GS). Maslach burnout inventory manual (1996)."},{"key":"e_1_3_3_2_103_2","doi-asserted-by":"crossref","unstructured":"Claire\u00a0M Segijn Eunah Kim Asma Sifaoui and Sophie\u00a0C Boerman. 2023. When you realize that big brother is watching: How informing consumers affects synced advertising effectiveness. Journal of Marketing Communications 29 4 (2023) 317\u2013338.","DOI":"10.1080\/13527266.2021.2020149"},{"key":"e_1_3_3_2_104_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-eacl.54"},{"key":"e_1_3_3_2_105_2","unstructured":"Li Siyan Vethavikashini\u00a0Chithrra Raghuram Omar Khattab Julia Hirschberg and Zhou Yu. 2024. PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.17127 (2024)."},{"key":"e_1_3_3_2_106_2","doi-asserted-by":"crossref","unstructured":"H\u00a0Jeff Smith Sandra\u00a0J Milberg and Sandra\u00a0J Burke. 1996. Information privacy: Measuring individuals\u2019 concerns about organizational practices. MIS quarterly (1996) 167\u2013196.","DOI":"10.2307\/249477"},{"key":"e_1_3_3_2_107_2","unstructured":"Luca Soldaini Rodney Kinney Akshita Bhagia Dustin Schwenk David Atkinson Russell Authur Ben Bogin Khyathi Chandu Jennifer Dumas Yanai Elazar et\u00a0al. 2024. Dolma: An open corpus of three trillion tokens for language model pretraining research. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.00159 (2024)."},{"key":"e_1_3_3_2_108_2","doi-asserted-by":"crossref","unstructured":"Daniel\u00a0J Solove. 2021. The myth of the privacy paradox. Geo. Wash. L. Rev. 89 (2021) 1.","DOI":"10.2139\/ssrn.3536265"},{"key":"e_1_3_3_2_109_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713783"},{"key":"e_1_3_3_2_110_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.trustnlp-1.18"},{"key":"e_1_3_3_2_111_2","unstructured":"Xiongtao Sun Gan Liu Zhipeng He Hui Li and Xiaoguang Li. 2024. DePrompt: Desensitization and Evaluation of Personal Identifiable Information in Large Language Model Prompts. arXiv:https:\/\/arXiv.org\/abs\/2408.08930 (2024)."},{"key":"e_1_3_3_2_112_2","volume-title":"Anthropic Economic Index: September 2025 Report \u2013 Uneven geographic and enterprise AI adoption","author":"Team Anthropic\u00a0Research","year":"2025","unstructured":"Anthropic\u00a0Research Team. 2025. Anthropic Economic Index: September 2025 Report \u2013 Uneven geographic and enterprise AI adoption. Research Report. Anthropic. https:\/\/www.anthropic.com\/research\/anthropic-economic-index-september-2025-report"},{"key":"e_1_3_3_2_113_2","unstructured":"Tencent\u00a0Hunyuan Team Ao Liu Botong Zhou Can Xu Chayse Zhou ChenChen Zhang Chengcheng Xu Chenhao Wang Decheng Wu Dengpeng Wu et\u00a0al. 2025. Hunyuan-turbos: Advancing large language models through mamba-transformer synergy and adaptive chain-of-thought. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.15431 (2025)."},{"key":"e_1_3_3_2_114_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et\u00a0al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.09288 (2023)."},{"key":"e_1_3_3_2_115_2","volume-title":"The Grandma Exploit Explained","year":"2025","unstructured":"Unknown. 2025. The Grandma Exploit Explained. https:\/\/jailbreakai.substack.com\/p\/the-grandma-exploit-explained-prompt Accessed: 2025-09-10; Substack article, author not specified."},{"key":"e_1_3_3_2_116_2","unstructured":"Davide Venditti Elena\u00a0Sofia Ruzzetti Giancarlo\u00a0A Xompero Cristina Giannone Andrea Favalli Raniero Romagnoli and Fabio\u00a0Massimo Zanzotto. 2024. Enhancing Data Privacy in Large Language Models through Private Association Editing. arXiv:https:\/\/arXiv.org\/abs\/2406.18221 (2024)."},{"key":"e_1_3_3_2_117_2","volume-title":"NeurIPS","author":"Wang Boxin","year":"2023","unstructured":"Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, et\u00a0al. 2023. DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models.. In NeurIPS."},{"key":"e_1_3_3_2_118_2","unstructured":"Ben Wang and Aran Komatsuzaki. 2021. GPT-J-6B: A 6 billion parameter autoregressive language model."},{"key":"e_1_3_3_2_119_2","unstructured":"Shang Wang Tianqing Zhu Bo Liu Ming Ding Xu Guo Dayong Ye Wanlei Zhou and Philip\u00a0S Yu. 2024. Unique security and privacy threats of large language model: A comprehensive survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.07973 (2024)."},{"key":"e_1_3_3_2_120_2","doi-asserted-by":"crossref","unstructured":"Maurice Weber Dan Fu Quentin Anthony Yonatan Oren Shane Adams Anton Alexandrov Xiaozhong Lyu Huu Nguyen Xiaozhe Yao Virginia Adams et\u00a0al. 2024. Redpajama: an open dataset for training large language models. Advances in neural information processing systems 37 (2024) 116462\u2013116492.","DOI":"10.52202\/079017-3697"},{"key":"e_1_3_3_2_121_2","unstructured":"Xinwei Wu Junzhuo Li Minghui Xu Weilong Dong Shuangzhi Wu Chao Bian and Deyi Xiong. 2023. Depn: Detecting and editing privacy neurons in pretrained language models. arXiv:https:\/\/arXiv.org\/abs\/2310.20138 (2023)."},{"key":"e_1_3_3_2_122_2","doi-asserted-by":"crossref","unstructured":"Zhong Yao Liantan Duan Shuo Xu Lingyi Chi and Dongfang Sheng. 2025. Performance of Large Language Models in the Non-English Context: Qualitative Study of Models Trained on Different Languages in Chinese Medical Examinations. JMIR Medical Informatics 13 1 (2025) e69485.","DOI":"10.2196\/69485"},{"key":"e_1_3_3_2_123_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642385"},{"key":"e_1_3_3_2_124_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.709"},{"key":"e_1_3_3_2_125_2","unstructured":"Jijie Zhou Eryue Xu Yaoyao Wu and Tianshi Li. 2024. Rescriber: Smaller-LLM-Powered User-Led Data Minimization for Navigating Privacy Trade-offs in LLM-Based Conversational Agent. arXiv:https:\/\/arXiv.org\/abs\/2410.11876 (2024)."},{"key":"e_1_3_3_2_126_2","doi-asserted-by":"crossref","unstructured":"John\u00a0JianJun Zhu Ling Tuo Yanfen You Qiang Fei and Matthew Thomson. 2024. A preemptive and curative solution to mitigate data breaches: Corporate social responsibility as a double layer of protection. Journal of Marketing Research 61 4 (2024) 778\u2013801.","DOI":"10.1177\/00222437231218969"},{"key":"e_1_3_3_2_127_2","unstructured":"Wenhao Zhu Yunzhe Lv Qingxiu Dong Fei Yuan Jingjing Xu Shujian Huang Lingpeng Kong Jiajun Chen and Lei Li. 2023. Extrapolating large language models to non-english by aligning languages. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.04948 (2023)."},{"key":"e_1_3_3_2_128_2","doi-asserted-by":"crossref","unstructured":"Yixin Zou Khue Le Peter Mayer Alessandro Acquisti Adam\u00a0J Aviv and Florian Schaub. 2024. Encouraging users to change breached passwords using the protection motivation theory. ACM Transactions on Computer-Human Interaction 31 5 (2024) 1\u201345.","DOI":"10.1145\/3689432"}],"event":{"name":"CHI 2026: CHI Conference on Human Factors in Computing Systems","location":"Barcelona Spain","acronym":"CHI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772318.3791809","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T10:52:08Z","timestamp":1781002328000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772318.3791809"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":127,"alternative-id":["10.1145\/3772318.3791809","10.1145\/3772318"],"URL":"https:\/\/doi.org\/10.1145\/3772318.3791809","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}