{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:18:47Z","timestamp":1777130327449,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","award":["202308440220"],"award-info":[{"award-number":["202308440220"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,22]]},"DOI":"10.1145\/3705328.3748155","type":"proceedings-article","created":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T10:48:44Z","timestamp":1757155724000},"page":"822-831","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Rethinking the Privacy of Text Embeddings: A Reproducibility Study of \u201cText Embeddings Reveal (Almost) As Much As Text\u201d"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9720-1788","authenticated-orcid":false,"given":"Dominykas","family":"Seputis","sequence":"first","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6837-6184","authenticated-orcid":false,"given":"Yongkang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6673-0846","authenticated-orcid":false,"given":"Karsten","family":"Langerak","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4245-497X","authenticated-orcid":false,"given":"Serghei","family":"Mihailov","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}]}],"member":"320","published-online":{"date-parts":[[2025,9,7]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","unstructured":"Mohamed Abdalla Moustafa Abdalla Graeme Hirst and Frank Rudzicz. 2020. Exploring the Privacy-Preserving Properties of Word Embeddings: Algorithmic Validation Study. J Med Internet Res 22 7 (15 Jul 2020) e18055. 10.2196\/18055","DOI":"10.2196\/18055"},{"key":"e_1_3_3_2_3_2","unstructured":"Bhavik B. 2019. Password Strength Classifier Dataset. Kaggle. https:\/\/www.kaggle.com\/datasets\/bhavikbb\/password-strength-classifier-dataset Accessed: 2025-05-08."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-30671-1_58"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.ACL-LONG.422"},{"key":"e_1_3_3_2_6_2","first-page":"30318","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Dettmers Tim","year":"2022","unstructured":"Tim Dettmers, Mike Lewis, Younes Belkada, and Luke Zettlemoyer. 2022. GPT3.int8(): 8-bit Matrix Multiplication for Transformers at Scale. In Advances in Neural Information Processing Systems , S.\u00a0Koyejo, S.\u00a0Mohamed, A.\u00a0Agarwal, D.\u00a0Belgrave, K.\u00a0Cho, and A.\u00a0Oh (Eds.), Vol.\u00a035. Curran Associates, Inc., 30318\u201330332. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/c3ba4962c05c49636d4c6206a97e9c8a-Paper-Conference.pdf"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/N19-1423"},{"key":"e_1_3_3_2_8_2","unstructured":"Thomas Diggelmann Jordan\u00a0L. Boyd-Graber Jannis Bulian Massimiliano Ciaramita and Markus Leippold. 2020. CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims. CoRR abs\/2012.00614 (2020). arXiv:https:\/\/arXiv.org\/abs\/2012.00614https:\/\/arxiv.org\/abs\/2012.00614"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.522"},{"key":"e_1_3_3_2_10_2","unstructured":"Matthijs Douze Alexandr Guzhva Chengqi Deng Jeff Johnson Gergely Szilvasy Pierre-Emmanuel Mazar\u00e9 Maria Lomeli Lucas Hosseini and Herv\u00e9 J\u00e9gou. 2024. The Faiss library. (2024). arxiv:https:\/\/arXiv.org\/abs\/2401.08281\u00a0[cs.LG]"},{"key":"e_1_3_3_2_11_2","unstructured":"Shankar Iyer Nikhil Dandekar and Korn\u00e9l Csernai. 2017. First Quora Dataset Release: Question Pairs. https:\/\/quoradata.quora.com\/First-Quora-Dataset-Release-Question-Pairs"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Alistair\u00a0EW Johnson Tom\u00a0J Pollard Lu Shen Li-wei\u00a0H Lehman Mengling Feng Mohammad Ghassemi Benjamin Moody Peter Szolovits Leo Anthony\u00a0Celi and Roger\u00a0G Mark. 2016. MIMIC-III a freely accessible critical care database. Scientific data 3 1 (2016) 1\u20139. 10.1038\/sdata.2016.35","DOI":"10.1038\/sdata.2016.35"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2020.EMNLP-MAIN.550"},{"key":"e_1_3_3_2_14_2","unstructured":"Dimitris Kastaniotis. 2022. Introduction to Weight Quantization. Towards Data Science. https:\/\/towardsdatascience.com\/introduction-to-weight-quantization-2494701b9c0c\/ Accessed: 2025\/07\/10 12:47:00."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_3_2_16_2","first-page":"3294","volume-title":"Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada","author":"Kiros Ryan","year":"2015","unstructured":"Ryan Kiros, Yukun Zhu, Ruslan Salakhutdinov, Richard\u00a0S. Zemel, Raquel Urtasun, Antonio Torralba, and Sanja Fidler. 2015. Skip-Thought Vectors. In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada, Corinna Cortes, Neil\u00a0D. Lawrence, Daniel\u00a0D. Lee, Masashi Sugiyama, and Roman Garnett (Eds.). 3294\u20133302. https:\/\/proceedings.neurips.cc\/paper\/2015\/hash\/f442d33fa06832082290ad8544a8da27-Abstract.html"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","unstructured":"Tom Kwiatkowski Jennimaria Palomaki Olivia Redfield Michael Collins Ankur\u00a0P. Parikh Chris Alberti Danielle Epstein Illia Polosukhin Jacob Devlin Kenton Lee Kristina Toutanova Llion Jones Matthew Kelcey Ming-Wei Chang Andrew\u00a0M. Dai Jakob Uszkoreit Quoc Le and Slav Petrov. 2019. Natural Questions: a Benchmark for Question Answering Research. Trans. Assoc. Comput. Linguistics 7 (2019) 452\u2013466. 10.1162\/TACL_A_00276","DOI":"10.1162\/TACL_A_00276"},{"key":"e_1_3_3_2_18_2","series-title":"JMLR Workshop and Conference Proceedings","first-page":"1188","volume-title":"Proceedings of the 31th International Conference on Machine Learning, ICML 2014, Beijing, China, 21-26 June 2014","volume":"32","author":"Le Quoc\u00a0V.","year":"2014","unstructured":"Quoc\u00a0V. Le and Tom\u00e1s Mikolov. 2014. Distributed Representations of Sentences and Documents. In Proceedings of the 31th International Conference on Machine Learning, ICML 2014, Beijing, China, 21-26 June 2014(JMLR Workshop and Conference Proceedings, Vol.\u00a032). JMLR.org, 1188\u20131196. http:\/\/proceedings.mlr.press\/v32\/le14.html"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2021.NAACL-MAIN.73"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"Yibin Lei Tao Shen Yu Cao and Andrew Yates. 2025. Enhancing Lexicon-Based Text Embeddings with Large Language Models. CoRR abs\/2501.09749 (2025). 10.48550\/ARXIV.2501.09749 arXiv:https:\/\/arXiv.org\/abs\/2501.09749","DOI":"10.48550\/ARXIV.2501.09749"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.ACL-LONG.546"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.FINDINGS-ACL.881"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-88717-8_8"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730110"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657951"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3192301"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/P19-1269"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/D16-1096"},{"key":"e_1_3_3_2_30_2","volume-title":"1st International Conference on Learning Representations, ICLR 2013, Scottsdale, Arizona, USA, May 2-4, 2013, Workshop Track Proceedings","author":"Mikolov Tom\u00e1s","year":"2013","unstructured":"Tom\u00e1s Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. In 1st International Conference on Learning Representations, ICLR 2013, Scottsdale, Arizona, USA, May 2-4, 2013, Workshop Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1301.3781"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.EMNLP-MAIN.765"},{"key":"e_1_3_3_2_32_2","unstructured":"Tri Nguyen Mir Rosenberg Xia Song Jianfeng Gao Saurabh Tiwary Rangan Majumder and Li Deng. 2016. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. CoRR abs\/1611.09268 (2016). arxiv:https:\/\/arXiv.org\/abs\/1611.09268http:\/\/arxiv.org\/abs\/1611.09268"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2022.EMNLP-MAIN.669"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098108"},{"key":"e_1_3_3_2_35_2","unstructured":"OpenAI. 2022. New and improved embedding model. https:\/\/openai.com\/index\/new-and-improved-embedding-model\/. Accessed: 2025-05-06."},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2022.ACL-SHORT.61"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.3115\/V1\/D14-1162"},{"key":"e_1_3_3_2_39_2","unstructured":"Qdrant Team. 2023. Qdrant: High-performance massive-scale vector database and vector search engine. https:\/\/qdrant.tech\/. Accessed: 2025-05-06."},{"key":"e_1_3_3_2_40_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. J. Mach. Learn. Res. 21 (2020) 140:1\u2013140:67. https:\/\/jmlr.org\/papers\/v21\/20-074.html"},{"key":"e_1_3_3_2_41_2","series-title":"NIST Special Publication","volume-title":"Proceedings of the Twenty-Seventh Text REtrieval Conference, TREC 2018, Gaithersburg, Maryland, USA, November 14-16, 2018","volume":"500","author":"Soboroff Ian","year":"2018","unstructured":"Ian Soboroff, Shudong Huang, and Donna Harman. 2018. TREC 2018 News Track Overview. In Proceedings of the Twenty-Seventh Text REtrieval Conference, TREC 2018, Gaithersburg, Maryland, USA, November 14-16, 2018(NIST Special Publication, Vol.\u00a0500-331), Ellen\u00a0M. Voorhees and Angela Ellis (Eds.). National Institute of Standards and Technology (NIST). https:\/\/trec.nist.gov\/pubs\/trec27\/papers\/Overview-News.pdf"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417270"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-76941-7_76"},{"key":"e_1_3_3_2_44_2","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). https:\/\/openreview.net\/forum?id=wCu6T5xFjeJ"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","unstructured":"George Tsatsaronis Georgios Balikas Prodromos Malakasiotis Ioannis Partalas Matthias Zschunke Michael\u00a0R. Alvers Dirk Weissenborn Anastasia Krithara Sergios Petridis Dimitris Polychronopoulos Yannis Almirantis John Pavlopoulos Nicolas Baskiotis Patrick Gallinari Thierry Arti\u00e8res Axel-Cyrille\u00a0Ngonga Ngomo Norman Heino \u00c9ric Gaussier Liliana Barrio-Alvers Michael Schroeder Ion Androutsopoulos and Georgios Paliouras. 2015. An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competition. BMC Bioinform. 16 (2015) 138:1\u2013138:28. 10.1186\/S12859-015-0564-6","DOI":"10.1186\/S12859-015-0564-6"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2014.23103"},{"key":"e_1_3_3_2_47_2","series-title":"NIST Special Publication","first-page":"69","volume-title":"Proceedings of The Twelfth Text REtrieval Conference, TREC 2003, Gaithersburg, Maryland, USA, November 18-21, 2003","volume":"500","author":"Voorhees Ellen\u00a0M.","year":"2003","unstructured":"Ellen\u00a0M. Voorhees. 2003. Overview of the TREC 2003 Robust Retrieval Track. In Proceedings of The Twelfth Text REtrieval Conference, TREC 2003, Gaithersburg, Maryland, USA, November 18-21, 2003(NIST Special Publication, Vol.\u00a0500-255), Ellen\u00a0M. Voorhees and Lori\u00a0P. Buckland (Eds.). National Institute of Standards and Technology (NIST), 69\u201377. http:\/\/trec.nist.gov\/pubs\/trec12\/papers\/ROBUST.OVERVIEW.pdf"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1023"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2020.EMNLP-MAIN.609"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.ACL-LONG.125"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","unstructured":"Yangde Wang Weidong Qiu Peng Tang Hao Tian and Shujun Li. 2025. SE#PCFG: Semantically Enhanced PCFG for Password Analysis and Cracking. IEEE Transactions on Dependable and Secure Computing (2025) 1\u201314. 10.1109\/TDSC.2025.3547773","DOI":"10.1109\/TDSC.2025.3547773"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463069"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.534"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939673"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3673791.3698414"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","unstructured":"Shengyao Zhuang Bevan Koopman and Guido Zuccon. 2024. Does Vec2Text Pose a New Corpus Poisoning Threat? CoRR abs\/2410.06628 (2024). 10.48550\/ARXIV.2410.06628","DOI":"10.48550\/ARXIV.2410.06628"}],"event":{"name":"RecSys '25: Nineteenth ACM Conference on Recommender Systems","location":"Prague Czech Republic","acronym":"RecSys '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGAI ACM Special Interest Group on Artificial Intelligence","SIGIR ACM Special Interest Group on Information Retrieval","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the Nineteenth ACM Conference on Recommender Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3705328.3748155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T11:50:47Z","timestamp":1757159447000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3705328.3748155"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,7]]},"references-count":55,"alternative-id":["10.1145\/3705328.3748155","10.1145\/3705328"],"URL":"https:\/\/doi.org\/10.1145\/3705328.3748155","relation":{},"subject":[],"published":{"date-parts":[[2025,9,7]]},"assertion":[{"value":"2025-09-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}