{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:53:09Z","timestamp":1778028789513,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T00:00:00Z","timestamp":1745539200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Google"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,26]]},"DOI":"10.1145\/3706598.3713701","type":"proceedings-article","created":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T14:48:11Z","timestamp":1745851691000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["Rescriber: Smaller-LLM-Powered User-Led Data Minimization for LLM-Based Chatbots"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0393-6195","authenticated-orcid":false,"given":"Jijie","family":"Zhou","sequence":"first","affiliation":[{"name":"Khoury College of Computer Sciences, Northeastern University, Boston, Massachusetts, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0255-0614","authenticated-orcid":false,"given":"Eryue","family":"Xu","sequence":"additional","affiliation":[{"name":"Khoury College of Computer Sciences, Northeastern University, Boston, Massachusetts, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7429-0414","authenticated-orcid":false,"given":"Yaoyao","family":"Wu","sequence":"additional","affiliation":[{"name":"Khoury College of Computer Sciences, Northeastern University, Boston, Massachusetts, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0877-5727","authenticated-orcid":false,"given":"Tianshi","family":"Li","sequence":"additional","affiliation":[{"name":"Khoury College of Computer Sciences, Northeastern University, Boston, Massachusetts, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,4,25]]},"reference":[{"key":"e_1_3_3_3_2_2","unstructured":"2024. Private Cloud Compute: A new frontier for AI privacy in the cloud. https:\/\/security.apple.com\/blog\/private-cloud-compute\/ Accessed: 2024-09-07."},{"key":"e_1_3_3_3_3_2","unstructured":"AI4Privacy. 2023. PII Masking 200K Dataset. https:\/\/huggingface.co\/datasets\/ai4privacy\/pii-masking-200k Accessed: 2024-09-07."},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"crossref","unstructured":"Hugh Beyer and Karen Holtzblatt. 1999. Contextual design. interactions 6 1 (1999) 32\u201342.","DOI":"10.1145\/291224.291229"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401034"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","unstructured":"Hee-Seung\u00a0Henry Bom. 2023. Exploring the Opportunities and Challenges of ChatGPT in Academic Writing: a Roundtable Discussion. Nuclear Medicine and Molecular Imaging 57 4 (May 2023) 165\u00e2\u20ac\u201c167. 10.1007\/s13139-023-00809-2","DOI":"10.1007\/s13139-023-00809-2"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3534642"},{"key":"e_1_3_3_3_8_2","unstructured":"S\u00e9bastien Bubeck Varun Chandrasekaran Ronen Eldan Johannes Gehrke Eric Horvitz Ece Kamar Peter Lee Yin\u00a0Tat Lee Yuanzhi Li Scott Lundberg et\u00a0al. 2023. Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.12712 (2023)."},{"key":"e_1_3_3_3_9_2","unstructured":"Nicholas Carlini Daphne Ippolito Matthew Jagielski Katherine Lee Florian Tramer and Chiyuan Zhang. 2022. Quantifying memorization across neural language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2202.07646 (2022)."},{"key":"e_1_3_3_3_10_2","volume-title":"USENIX Security Symposium","author":"Carlini Nicholas","year":"2021","unstructured":"Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom\u00a0B Brown, Dawn Song, Ulfar Erlingsson, et\u00a0al. 2021. Extracting Training Data from Large Language Models.. In USENIX Security Symposium , Vol.\u00a06."},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"crossref","unstructured":"Szu-Wei Cheng Chung-Wen Chang Wan-Jung Chang Hao-Wei Wang Chih-Sung Liang Taishiro Kishimoto Jane Pei-Chen Chang John\u00a0S Kuo and Kuan-Pin Su. 2023. The now and future of ChatGPT and GPT in psychiatry. Psychiatry and clinical neurosciences 77 11 (2023) 592\u2013596.","DOI":"10.1111\/pcn.13588"},{"key":"e_1_3_3_3_12_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 preprint arXiv:https:\/\/arXiv.org\/abs\/2408.07004 (2024)."},{"key":"e_1_3_3_3_13_2","first-page":"2473","volume-title":"32nd USENIX Security Symposium (USENIX Security 23)","author":"Do Youngwook","year":"2023","unstructured":"Youngwook Do, Nivedita Arora, Ali Mirzazadeh, Injoo Moon, Eryue Xu, Zhihan Zhang, Gregory\u00a0D Abowd, and Sauvik Das. 2023. Powering for privacy: improving user trust in smart speaker microphones with intentional powering and perceptible assurance. In 32nd USENIX Security Symposium (USENIX Security 23). 2473\u20132490."},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","unstructured":"Youngwook Do Jung\u00a0Wook Park Yuxi Wu Avinandan Basu Dingtian Zhang Gregory\u00a0D. Abowd and Sauvik Das. 2021. Smart Webcam Cover: Exploring the Design of an Intelligent Webcam Cover to Improve Usability and Trust: Exploring the Design of an Intelligent Webcam Cover to Improve Usability and Trust. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 5 4 (December 2021) 1\u00e2\u20ac\u201c21. 10.1145\/3494983","DOI":"10.1145\/3494983"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.741"},{"key":"e_1_3_3_3_16_2","unstructured":"Federal Privacy Council. 2023. Fair Information Practice Principles (FIPPs). https:\/\/www.fpc.gov\/resources\/fipps\/ Accessed: 2024-09-07."},{"key":"e_1_3_3_3_17_2","unstructured":"James\u00a0W Gentry. 1990. What is experiential learning. Guide to business gaming and experiential learning 9 1 (1990) 20\u201332."},{"key":"e_1_3_3_3_18_2","unstructured":"Google. 2023. Introducing Gemini: our largest and most capable AI model. https:\/\/blog.google\/technology\/ai\/google-gemini-ai\/ Accessed: 2024-09-07."},{"key":"e_1_3_3_3_19_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 preprint arXiv:https:\/\/arXiv.org\/abs\/2210.01504 (2022)."},{"key":"e_1_3_3_3_20_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_3_21_2","doi-asserted-by":"publisher","unstructured":"Nir Kshetri. 2023. Cybercrime and Privacy Threats of Large Language Models. IT Professional 25 3 (May 2023) 9\u00e2\u20ac\u201c13. 10.1109\/mitp.2023.3275489","DOI":"10.1109\/mitp.2023.3275489"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2481287"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","unstructured":"Tianshi Li Yuvraj Agarwal and Jason\u00a0I. Hong. 2018. Coconut: An IDE Plugin for Developing Privacy-Friendly Apps: An IDE Plugin for Developing Privacy-Friendly Apps. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 2 4 (December 2018) 1\u00e2\u20ac\u201c35. 10.1145\/3287056","DOI":"10.1145\/3287056"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3643983"},{"key":"e_1_3_3_3_25_2","unstructured":"Xuechen Li Florian Tramer Percy Liang and Tatsunori Hashimoto. 2021. Large language models can be strong differentially private learners. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2110.05679 (2021)."},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","unstructured":"Yuanchun Li Fanglin Chen Toby Jia-Jun Li Yao Guo Gang Huang Matthew Fredrikson Yuvraj Agarwal and Jason\u00a0I. Hong. 2017. PrivacyStreams: Enabling Transparency in Personal Data Processing for Mobile Apps: Enabling Transparency in Personal Data Processing for Mobile Apps. Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies 1 3 (September 2017) 1\u201326. 10.1145\/3130941","DOI":"10.1145\/3130941"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.323"},{"key":"e_1_3_3_3_28_2","unstructured":"Jimit Majmudar Christophe Dupuy Charith Peris Sami Smaili Rahul Gupta and Richard Zemel. 2022. Differentially private decoding in large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.13621 (2022)."},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","unstructured":"Naresh\u00a0K. Malhotra Sung\u00a0S. Kim and James Agarwal. 2004. Internet Users\u2019 Information Privacy Concerns (IUIPC): The Construct the Scale and a Causal Model. Information Systems Research 15 4 (December 2004) 336\u2013355. 10.1287\/isre.1040.0032","DOI":"10.1287\/isre.1040.0032"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.957"},{"key":"e_1_3_3_3_31_2","unstructured":"Niloofar Mireshghallah Maria Antoniak Yash More Yejin Choi and Golnoosh Farnadi. 2024. Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild. arxiv:https:\/\/arXiv.org\/abs\/2407.11438\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2407.11438"},{"key":"e_1_3_3_3_32_2","unstructured":"Niloofar Mireshghallah Maria Antoniak Yash More Yejin Choi and Golnoosh Farnadi. 2024. Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.11438 (2024)."},{"key":"e_1_3_3_3_33_2","unstructured":"Niloofar Mireshghallah Hyunwoo Kim Xuhui Zhou Yulia Tsvetkov Maarten Sap Reza Shokri and Yejin Choi. 2023. Can llms keep a secret? testing privacy implications of language models via contextual integrity theory. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.17884 (2023)."},{"key":"e_1_3_3_3_34_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 preprint arXiv:https:\/\/arXiv.org\/abs\/2311.17035 (2023)."},{"key":"e_1_3_3_3_35_2","unstructured":"Helen Nissenbaum. 2004. Privacy as contextual integrity. Wash. L. Rev. 79 (2004) 119."},{"key":"e_1_3_3_3_36_2","first-page":"292","volume-title":"Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)","author":"Olstad Annika\u00a0Willoch","year":"2023","unstructured":"Annika\u00a0Willoch Olstad, Anthi Papadopoulou, and Pierre Lison. 2023. Generation of Replacement Options in Text Sanitization. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa). 292\u2013300."},{"key":"e_1_3_3_3_37_2","unstructured":"OpenAI. 2022. Introducing ChatGPT. https:\/\/openai.com\/index\/chatgpt\/ Accessed: 2024-09-07."},{"key":"e_1_3_3_3_38_2","unstructured":"European Parliament and Council of\u00a0the European\u00a0Union. 2016. Regulation (EU) 2016\/679 of the European Parliament and of the Council of 27 April 2016 on the protection of natural persons with regard to the processing of personal data and on the free movement of such data and repealing Directive 95\/46\/EC (General Data Protection Regulation). https:\/\/eur-lex.europa.eu\/eli\/reg\/2016\/679\/oj Accessed: 2024-09-07."},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3575792"},{"key":"e_1_3_3_3_40_2","unstructured":"Bashir Rastegarpanah Krishna Gummadi and Mark Crovella. 2021. Auditing black-box prediction models for data minimization compliance. Advances in Neural Information Processing Systems 34 (2021) 20621\u201320632."},{"key":"e_1_3_3_3_41_2","unstructured":"RyokoAI. 2023. ShareGPT52K Dataset. https:\/\/huggingface.co\/datasets\/RyokoAI\/ShareGPT52K Accessed: 2024-09-07."},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"crossref","unstructured":"Peter Schaar. 2010. Privacy by design. Identity in the Information Society 3 2 (2010) 267\u2013274.","DOI":"10.1007\/s12394-010-0055-x"},{"key":"e_1_3_3_3_43_2","unstructured":"Rylan Schaeffer Brando Miranda and Sanmi Koyejo. 2024. Are emergent abilities of large language models a mirage? Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_3_44_2","unstructured":"Awanthika Senarath and Nalin Asanka\u00a0Gamagedara Arachchilage. 2018. Understanding software developers\u2019 approach towards implementing data minimization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1808.01479 (2018)."},{"key":"e_1_3_3_3_45_2","unstructured":"Yijia Shao Tianshi Li Weiyan Shi Yanchen Liu and Diyi Yang. 2024. PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.00138 (2024)."},{"key":"e_1_3_3_3_46_2","first-page":"2797","volume-title":"33rd USENIX Security Symposium (USENIX Security 24)","author":"Sharma Tanusree","year":"2024","unstructured":"Tanusree Sharma, Lin Kyi, Yang Wang, and Asia\u00a0J Biega. 2024. \" I\u2019m not convinced that they don\u2019t collect more than is necessary\":{ User-Controlled} Data Minimization Design in Search Engines. In 33rd USENIX Security Symposium (USENIX Security 24). 2797\u20132812."},{"key":"e_1_3_3_3_47_2","unstructured":"Adam Shostack. 2024. The Boy Who Survived: Removing Harry Potter from an LLM is harder than reported. arxiv:https:\/\/arXiv.org\/abs\/2403.12082\u00a0[cs.CL]"},{"key":"e_1_3_3_3_48_2","unstructured":"Robin Staab Mark Vero Mislav Balunovi\u0107 and Martin Vechev. 2023. Beyond memorization: Violating privacy via inference with large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.07298 (2023)."},{"key":"e_1_3_3_3_49_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar et\u00a0al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.13971 (2023)."},{"key":"e_1_3_3_3_50_2","unstructured":"Florian Tramer and Dan Boneh. 2018. Slalom: Fast verifiable and private execution of neural networks in trusted hardware. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1806.03287 (2018)."},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"crossref","unstructured":"Dinusha Vatsalan Peter Christen and Vassilios\u00a0S Verykios. 2013. A taxonomy of privacy-preserving record linkage techniques. Information Systems 38 6 (2013) 946\u2013969.","DOI":"10.1016\/j.is.2012.11.005"},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1017\/9781316888667"},{"key":"e_1_3_3_3_53_2","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama Maarten Bosma Denny Zhou Donald Metzler et\u00a0al. 2022. Emergent abilities of large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2206.07682 (2022)."},{"key":"e_1_3_3_3_54_2","unstructured":"Da Yu Saurabh Naik Arturs Backurs Sivakanth Gopi Huseyin\u00a0A Inan Gautam Kamath Janardhan Kulkarni Yin\u00a0Tat Lee Andre Manoel Lukas Wutschitz et\u00a0al. 2021. Differentially private fine-tuning of language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2110.06500 (2021)."},{"key":"e_1_3_3_3_55_2","unstructured":"Chiyuan Zhang Daphne Ippolito Katherine Lee Matthew Jagielski Florian Tram\u00e8r and Nicholas Carlini. 2021. Counterfactual memorization in neural language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2112.12938 (2021)."},{"key":"e_1_3_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642713"},{"key":"e_1_3_3_3_57_2","unstructured":"Zhiping Zhang Bingcan Guo and Tianshi Li. 2024. Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.01344 (2024)."},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642385"},{"key":"e_1_3_3_3_59_2","series-title":"(NIPS \u201923)","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Zheng Lianmin","year":"2024","unstructured":"Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric\u00a0P. Xing, Hao Zhang, Joseph\u00a0E. Gonzalez, and Ion Stoica. 2024. Judging LLM-as-a-judge with MT-bench and Chatbot Arena. In Proceedings of the 37th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS \u201923). Curran Associates Inc., Red Hook, NY, USA, Article 2020, 29\u00a0pages."}],"event":{"name":"CHI 2025: CHI Conference on Human Factors in Computing Systems","location":"Yokohama Japan","acronym":"CHI '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706598.3713701","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3706598.3713701","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T05:39:52Z","timestamp":1751607592000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706598.3713701"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,25]]},"references-count":58,"alternative-id":["10.1145\/3706598.3713701","10.1145\/3706598"],"URL":"https:\/\/doi.org\/10.1145\/3706598.3713701","relation":{},"subject":[],"published":{"date-parts":[[2025,4,25]]},"assertion":[{"value":"2025-04-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}