{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T19:06:14Z","timestamp":1779131174901,"version":"3.51.4"},"reference-count":83,"publisher":"Association for Computing Machinery (ACM)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Manag. Data"],"published-print":{"date-parts":[[2026,5,18]]},"abstract":"<jats:p>This paper addresses the challenge of protecting Personally Identifiable Information (PII) in textual data, identifying and anonymizing PII to ensure privacy and regulatory compliance, while preserving data utility. We model this bi-criteria optimization problem as a two-player Stackelberg game, where an attacker seeks to link anonymized data back to individuals and a protector anonymizes the data to prevent re-identification. We show that the problem is intractable. Thus we develop SHIELD, an attack-aware PII protection system that iteratively engages the protector and attacker to prevent both PII breaches and over-scrubbing. SHIELD integrates logical reasoning with machine learning to identify PII, and supports pluggable attackers for robustness against re-identification. It achieves a constant-factor approximation for utility loss while mitigating risk. Using synthetic and real-world datasets, we empirically show that SHIELD offers better privacy-utility trade-off than prior PII protection systems, while remaining efficient and scalable.<\/jats:p>","DOI":"10.1145\/3802109","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T18:19:16Z","timestamp":1779128356000},"page":"1-28","source":"Crossref","is-referenced-by-count":0,"title":["Shielding PII to Prevent Re-identification and Preserve Utility"],"prefix":"10.1145","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4892-0979","authenticated-orcid":false,"given":"Shuhao","family":"Liu","sequence":"first","affiliation":[{"name":"Shenzhen Institute of Computing Sciences, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5149-2656","authenticated-orcid":false,"given":"Wenfei","family":"Fan","sequence":"additional","affiliation":[{"name":"Shenzhen Institute of Computing Sciences, Shenzhen, China and University of Edinburgh, Edinburgh, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0168-0012","authenticated-orcid":false,"given":"Yijia","family":"Xu","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,18]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"AI4Privacy. 2025. English Anonymiser OpenPII (Ai4Privacy ) on HuggingFace. https:\/\/huggingface.co\/ai4privacy\/llama-ai4privacy-english-anonymiser-openpii"},{"key":"e_1_2_1_2_1","volume-title":"Conference of the North American Chapter, of the Association, for Computational Linguistics: Human Language Technologies (NAACL-HLT). 54-59","author":"Akbik Alan","year":"2019","unstructured":"Alan Akbik, Tanja Bergmann, Duncan Blythe, Kashif Rasul, Stefan Schweter, and Roland Vollgraf. 2019. FLAIR: An Easy-to-Use Framework, for State-of-the-Art NLP. In Conference of the North American Chapter, of the Association, for Computational Linguistics: Human Language Technologies (NAACL-HLT). 54-59."},{"key":"e_1_2_1_3_1","first-page":"3","article-title":"T-Plausibility: Generalizing Words, to Desensitize Text","volume":"5","author":"Anandan Balamurugan","year":"2012","unstructured":"Balamurugan Anandan, Chris Clifton, Wei Jiang, Mummoorthy Murugesan, Pedro Pastrana-Camacho, and Luo Si. 2012. T-Plausibility: Generalizing Words, to Desensitize Text. Transaction on Data Privacy (TDP), Vol. 5, 3 (Dec. 2012), 505-534.","journal-title":"Transaction on Data Privacy (TDP)"},{"key":"e_1_2_1_4_1","volume-title":"Consistent Query Answers in Inconsistent Databases. In Symposium on Principles of Database Systems (PODS). 68-79","author":"Arenas Marcelo","year":"1999","unstructured":"Marcelo Arenas, Leopoldo Bertossi, and Jan Chomicki. 1999. Consistent Query Answers in Inconsistent Databases. In Symposium on Principles of Database Systems (PODS). 68-79."},{"key":"e_1_2_1_5_1","volume-title":"AAAI Workshop, on Privacy-Preserving Artificial Intelligence (PPAI, ). arXiv:2501","author":"Asthana Shubhi","year":"2025","unstructured":"Shubhi Asthana, Ruchi Mahindru, Bing Zhang, and Jorge Sanz. 2025. Adaptive PII Mitigation Framework, for Large Language Models. In AAAI Workshop, on Privacy-Preserving Artificial Intelligence (PPAI, ). arXiv:2501.12465 [cs]"},{"key":"e_1_2_1_6_1","first-page":"1","article-title":"Enhancing the Utility of Anonymized Data by Improving the Quality of Generalization Hierarchies","volume":"10","author":"Ayala-Rivera Vanessa","year":"2017","unstructured":"Vanessa Ayala-Rivera, Patrick McDonagh, Thomas Cerqueus, Liam Murphy, and Christina Thorpe. 2017. Enhancing the Utility of Anonymized Data by Improving the Quality of Generalization Hierarchies. Transations on Data Privacy (TDP), Vol. 10, 1 (April 2017), 27-59.","journal-title":"Transations on Data Privacy (TDP)"},{"key":"e_1_2_1_7_1","unstructured":"California State Legislature. 2018. California Consumer Privacy Act. https:\/\/leginfo.legislature.ca.gov\/faces\/billTextClient.xhtml?bill_id=201720180AB375"},{"key":"e_1_2_1_8_1","volume-title":"Hamido Fujita, and Massimo Esposito.","author":"Catelli Rosario","year":"2021","unstructured":"Rosario Catelli, Valentina Casola, Giuseppe De Pietro, Hamido Fujita, and Massimo Esposito. 2021. Combining Contextualized Word Representation and Sub-Document Level Analysis through Bi-LS\u2122CRF, Architecture for Clinical de-Identification. Knowledge-Based Systems, Vol. 213 (Feb. 2021), 106649."},{"key":"e_1_2_1_9_1","volume-title":"Efficient Techniques for Document Sanitization. In ACM Conference, on Information, and Knowledge Management (CIKM). 843-852","author":"Chakaravarthy Venkatesan T.","unstructured":"Venkatesan T. Chakaravarthy, Himanshu Gupta, Prasan Roy, and Mukesh K. Mohania. 2008. Efficient Techniques for Document Sanitization. In ACM Conference, on Information, and Knowledge Management (CIKM). 843-852."},{"key":"e_1_2_1_10_1","volume-title":"Proc. ACM Manag. Data (SIGMOD)","volume":"3","author":"Chen Shenglin","year":"2025","unstructured":"Shenglin Chen, Wenfei Fan, and Ruochun Jin. 2025. Outliers: The Good, the Bad and the Ugly. Proc. ACM Manag. Data (SIGMOD), Vol. 3, 4 (2025), 259:1-259:30."},{"key":"e_1_2_1_11_1","volume-title":"Annual Meeting, of the Association, for Computational Linguistics (ACL). 15607-15631","author":"Chiang Cheng-Han","year":"2023","unstructured":"Cheng-Han Chiang and Hung-yi Lee. 2023. Can Large Language Models Be an Alternative to Human Evaluations?. In Annual Meeting, of the Association, for Computational Linguistics (ACL). 15607-15631."},{"key":"e_1_2_1_12_1","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1162\/tacl_a_00104","article-title":"Named Entity Recognition, with Bidirectional LSTM-CNNs","volume":"4","author":"Chiu Jason P.C.","year":"2016","unstructured":"Jason P.C. Chiu and Eric Nichols. 2016. Named Entity Recognition, with Bidirectional LSTM-CNNs. Transactions of the Association for Computational Linguistics (TACL), Vol. 4 (2016), 357-370.","journal-title":"Transactions of the Association for Computational Linguistics (TACL)"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.4.3.233"},{"key":"e_1_2_1_14_1","volume-title":"Annual Meeting, of the Association, for Computational Linguistics (ACL). 8440-8451","author":"Conneau Alexis","year":"2020","unstructured":"Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzm\u00e1n, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. Unsupervised Cross-Lingual Representation Learning at Scale. In Annual Meeting, of the Association, for Computational Linguistics (ACL). 8440-8451."},{"key":"e_1_2_1_15_1","unstructured":"M. Mikail Demir Hakan T. Otal and M. Abdullah Canbaz. 2025. LegalGuardian: A Privacy-Preserving Framework for Secure Integration of Large Language Models in Legal Practice. arXiv:2501.10915 [cs] http:\/\/arxiv.org\/abs\/2501.10915"},{"key":"e_1_2_1_16_1","doi-asserted-by":"crossref","first-page":"596","DOI":"10.1093\/jamia\/ocw156","article-title":"De-Identification of Patient Notes with Recurrent Neural Networks","volume":"24","author":"Dernoncourt Franck","year":"2017","unstructured":"Franck Dernoncourt, Ji Young Lee, Ozlem Uzuner, and Peter Szolovits. 2017. De-Identification of Patient Notes with Recurrent Neural Networks. Journal of the American Medical Informatics Association (JAMIA), Vol. 24, 3 (2017), 596-606.","journal-title":"Journal of the American Medical Informatics Association (JAMIA)"},{"key":"e_1_2_1_17_1","volume-title":"Annual Meeting, of the Association, for Computational Linguistics (ACL). 13732-13754","author":"Dou Yao","year":"2024","unstructured":"Yao Dou, Isadora Krsek, Tarek Naous, Anubha Kabra, Sauvik Das, Alan Ritter, and Wei Xu. 2024. Reducing Privacy Risks, in Online Self-Disclosures, with Language Models. In Annual Meeting, of the Association, for Computational Linguistics (ACL). 13732-13754."},{"key":"e_1_2_1_18_1","first-page":"265","article-title":"Calibrating Noise, to Sensitivity","author":"Dwork Cynthia","year":"2006","unstructured":"Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam Smith. 2006. Calibrating Noise, to Sensitivity, in Private Data Analysis. In Theory of Cryptography (TTC). 265-284.","journal-title":"Private Data Analysis. In Theory of Cryptography (TTC)."},{"key":"e_1_2_1_19_1","first-page":"3","article-title":"The Algorithmic Foundations, of Differential Privacy","volume":"9","author":"Dwork Cynthia","year":"2014","unstructured":"Cynthia Dwork and Aaron Roth. 2014. The Algorithmic Foundations, of Differential Privacy. Foundations and Trends in Theoretical Computer Science, Vol. 9, 3-4 (Aug. 2014), 211-407.","journal-title":"Foundations and Trends in Theoretical Computer Science"},{"key":"e_1_2_1_20_1","volume-title":"of","author":"European Parliament and Council of the European Union. 2016. Regulation (EU, ) 2016\/679 of the European Parliament, and of the Council","year":"2016","unstructured":"European Parliament and Council of the European Union. 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, ). 88 pages. https:\/\/eur-lex.europa.eu\/eli\/reg\/2016\/679\/oj"},{"key":"e_1_2_1_21_1","article-title":"Conditional functional dependencies for capturing data inconsistencies","volume":"33","author":"Fan Wenfei","year":"2008","unstructured":"Wenfei Fan, Floris Geerts, Xibei Jia, and Anastasios Kementsietsidis. 2008. Conditional functional dependencies for capturing data inconsistencies. ACM Trans. Database Syst. (TODS), Vol. 33, 2 (2008), 6:1-6:48.","journal-title":"ACM Trans. Database Syst. (TODS)"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-2917-1"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.14778\/3457390.3457400"},{"key":"e_1_2_1_24_1","volume-title":"AllenNLP: A Deep Semantic Natural Language Processing Platform. In Workshop for NLP Open Source Software (NLPOSS). 1-6.","author":"Gardner Matt","year":"2018","unstructured":"Matt Gardner, Joel Grus, Mark Neumann, Oyvind Tafjord, Pradeep Dasigi, Nelson F. Liu, Matthew Peters, Michael Schmitz, and Luke Zettlemoyer. 2018. AllenNLP: A Deep Semantic Natural Language Processing Platform. In Workshop for NLP Open Source Software (NLPOSS). 1-6."},{"key":"e_1_2_1_25_1","volume-title":"Computers and Intractability: A Guide to the Theory of NP-Completeness","author":"Garey Michael","unstructured":"Michael Garey and David Johnson. 1979. Computers and Intractability: A Guide to the Theory of NP-Completeness. W. H. Freeman and Company."},{"key":"e_1_2_1_26_1","unstructured":"Akshay Goel. 2025. LangExtract. https:\/\/github.com\/google\/langextract"},{"key":"e_1_2_1_27_1","volume-title":"Population. In ACM Workshop, on Privacy, in Electronic Society (WPES). 77-80","author":"Golle Philippe","year":"2006","unstructured":"Philippe Golle. 2006. Revisiting the Uniqueness of Simple Demographics in the US, Population. In ACM Workshop, on Privacy, in Electronic Society (WPES). 77-80."},{"key":"e_1_2_1_28_1","unstructured":"Government of Canada. 2000. Personal Information Protection and Electronic Documents Act. https:\/\/laws-lois.justice.gc.ca\/eng\/acts\/P-21\/FullText.html"},{"key":"e_1_2_1_29_1","unstructured":"Gretel AI. 2024. GLiNER Models for PII Detection through Fine-Tuning on Gretel-Generated Synthetic Documents. https:\/\/huggingface.co\/datasets\/gretelai\/gretel-pii-masking-en-v1"},{"key":"e_1_2_1_30_1","unstructured":"Jiawei Gu Xuhui Jiang Zhichao Shi Hexiang Tan Xuehao Zhai Chengjin Xu Wei Li Yinghan Shen Shengjie Ma Honghao Liu Saizhuo Wang Kun Zhang Yuanzhuo Wang Wen Gao Lionel Ni and Jian Guo. 2025. A Survey on LLM-as-a-Judge. arXiv:2411.15594 [cs] http:\/\/arxiv.org\/abs\/2411.15594"},{"key":"e_1_2_1_31_1","volume-title":"TANE: An efficient algorithm for discovering functional and approximate dependencies. Comput. J.","author":"Huhtala Yk\u00e4","year":"1999","unstructured":"Yk\u00e4 Huhtala, Juha K\u00e4rkk\u00e4inen, Pasi Porkka, and Hannu Toivonen. 1999. TANE: An efficient algorithm for discovering functional and approximate dependencies. Comput. J. (1999)."},{"key":"e_1_2_1_32_1","volume-title":"Findings of the","author":"Igamberdiev Timour","unstructured":"Timour Igamberdiev and Ivan Habernal. 2023. DP-BART, for Privatized Text Rewriting, under Local Differential Privacy. In Findings of the Association, for Computational Linguistics (ACL). 13914-13934."},{"key":"e_1_2_1_33_1","volume-title":"ACM Conference, on Computer, and Communications Security (CCS). 1505-1519","author":"Imola Jacob","year":"2022","unstructured":"Jacob Imola, Takao Murakami, and Kamalika Chaudhuri. 2022. Differentially Private Triangle, and 4-Cycle Counting, in the Shuffle Model. In ACM Conference, on Computer, and Communications Security (CCS). 1505-1519."},{"key":"e_1_2_1_34_1","volume-title":"Deidentification of Free-Text Medical Records Using Pre-Trained Bidirectional Transformers. In ACM Conference, on Health, Inference, and Learning (CHIL). 214-221","author":"Johnson Alistair E. W.","unstructured":"Alistair E. W. Johnson, Lucas Bulgarelli, and Tom J. Pollard. 2020. Deidentification of Free-Text Medical Records Using Pre-Trained Bidirectional Transformers. In ACM Conference, on Health, Inference, and Learning (CHIL). 214-221."},{"key":"e_1_2_1_35_1","volume-title":"Symposium on Operating Systems Principles (SOSP). 611-626","author":"Kwon Woosuk","year":"2023","unstructured":"Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient Memory Management, for Large Language Model Serving, with PagedAttention. In Symposium on Operating Systems Principles (SOSP). 611-626."},{"key":"e_1_2_1_36_1","first-page":"74","article-title":"ROUGE: A Package, for Automatic Evaluation, of Summaries","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package, for Automatic Evaluation, of Summaries. In Text Summarization Branches Out. 74-81.","journal-title":"Text Summarization Branches Out."},{"key":"e_1_2_1_37_1","volume-title":"Annual Meeting, of the Association, for Computational Linguistics (ACL). 4188-4203","author":"Lison Pierre","year":"2021","unstructured":"Pierre Lison, Ildik\u00f3 Pil\u00e1n, David Sanchez, Montserrat Batet, and Lilja \u00d8vrelid. 2021. Anonymisation Models, for Text Data: State, of the Art, Challenges, and Future Directions. In Annual Meeting, of the Association, for Computational Linguistics (ACL). 4188-4203."},{"key":"e_1_2_1_38_1","volume-title":"Interactive Journal of Medical Research (IJMR)","volume":"12","author":"Liu Leibo","year":"2023","unstructured":"Leibo Liu, Oscar Perez-Concha, Anthony Nguyen, Vicki Bennett, Victoria Blake, Blanca Gallego, and Louisa Jorm. 2023. Web-Based Application Based, on Human-in-the-Loop Deep Learning, for Deidentifying Free-Text Data, in Electronic Medical Records: Development, and Usability Study. Interactive Journal of Medical Research (IJMR), Vol. 12 (Aug. 2023), e46322."},{"key":"e_1_2_1_39_1","unstructured":"Shuhao Liu Wenfei Fan and Yijia Xu. 2026. Full version paper with appendices. https:\/\/shuhaoliu.github.io\/assets\/papers\/shuhao-sigmod26-shield-full.pdf."},{"key":"e_1_2_1_40_1","volume-title":"Farima Fatahi Bayat, and Lu Wang","author":"Liu Xin","year":"2024","unstructured":"Xin Liu, Farima Fatahi Bayat, and Lu Wang. 2024. Enhancing Language Model Factuality, via Activation-Based Confidence Calibration, and Guided Decoding. arXiv:2406.13230 [cs] http:\/\/arxiv.org\/abs\/2406.13230"},{"key":"e_1_2_1_41_1","article-title":"De-Identification of Clinical Notes via Recurrent Neural Network and Conditional Random Field","volume":"75","author":"Liu Zengjian","year":"2017","unstructured":"Zengjian Liu, Buzhou Tang, Xiaolong Wang, and Qingcai Chen. 2017. De-Identification of Clinical Notes via Recurrent Neural Network and Conditional Random Field. Journal of Biomedical Informatics (JBI), Vol. 75 (Nov. 2017), S34-S42.","journal-title":"Journal of Biomedical Informatics (JBI)"},{"key":"e_1_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Gabriel Loiseau Damien Sileo Damien Riquet Maxime Meyer and Marc Tommasi. 2025. Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymization. arXiv:2506.05979 [cs] http:\/\/arxiv.org\/abs\/2506.05979","DOI":"10.18653\/v1\/2025.emnlp-demos.16"},{"key":"e_1_2_1_43_1","volume-title":"Masking. In Workshop on Language Technology, for Equality, Diversity, and Inclusion (LTEDI). 76-89","author":"Mansfield Courtney","year":"2022","unstructured":"Courtney Mansfield, Amandalynne Paullada, and Kristen Howell. 2022. Behind the Mask: Demographic, Bias in Name Detection for PII, Masking. In Workshop on Language Technology, for Equality, Diversity, and Inclusion (LTEDI). 76-89."},{"key":"e_1_2_1_44_1","volume-title":"Findings of the","author":"Mattern Justus","unstructured":"Justus Mattern, Benjamin Weggenmann, and Florian Kerschbaum. 2022. The Limits, of Word Level Differential Privacy. In Findings of the Association, for Computational Linguistics (NAACL). 867-881."},{"key":"e_1_2_1_45_1","volume-title":"Romanello Matteo, and Doucet Antoine.","author":"Maud Ehrmann","year":"2023","unstructured":"Ehrmann Maud, Hamdi Ahmed, Elvys Linhares Pontes, Romanello Matteo, and Doucet Antoine. 2023. Named Entity Recognition, and Classification, in Historical Documents: A Survey. Comput. Surveys (Sept. 2023)."},{"key":"e_1_2_1_46_1","volume-title":"Findings of the","author":"Meisenbacher Stephen","unstructured":"Stephen Meisenbacher, Maulik Chevli, Juraj Vladika, and Florian Matthes. 2024. DP-MLM: Differentially Private Text Rewriting Using Masked Language Models. In Findings of the Association, for Computational Linguistics (ACL). 9314-9328."},{"key":"e_1_2_1_47_1","first-page":"4","article-title":"DEDUCE: A, Pattern Matching Method for Automatic de-Identification of Dutch","volume":"35","author":"Menger Vincent","year":"2018","unstructured":"Vincent Menger, Floor Scheepers, Lisette Maria Van Wijk, and Marco Spruit. 2018. DEDUCE: A, Pattern Matching Method for Automatic de-Identification of Dutch, Medical Text. Telematics and Informatics, Vol. 35, 4 (July 2018), 727-736.","journal-title":"Medical Text. Telematics and Informatics"},{"key":"e_1_2_1_48_1","volume-title":"Andrea Santilli, Fabio Massimo Zanzotto, Sebastien Bratieres, and Emanuele Rodola.","author":"Miranda Michele","year":"2025","unstructured":"Michele Miranda, Elena Sofia Ruzzetti, Andrea Santilli, Fabio Massimo Zanzotto, Sebastien Bratieres, and Emanuele Rodola. 2025. Preserving Privacy, in Large Language Models: A Survey, on Current Threats, and Solutions. Transactions on Machine Learning Research (TMLR) (2025)."},{"key":"e_1_2_1_49_1","unstructured":"Microsoft. 2025. Presidio. https:\/\/microsoft.github.io\/presidio\/"},{"key":"e_1_2_1_50_1","volume-title":"Findings of the","author":"Morris John","unstructured":"John Morris, Justin Chiu, Ramin Zabih, and Alexander Rush. 2022. Unsupervised Text Deidentification. In Findings of the Association, for Computational Linguistics (EMNLP). 4777-4788."},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6947-8-32"},{"key":"e_1_2_1_52_1","first-page":"1","article-title":"De-Identification of Free Text Data, Containing Personal Health Information: A Scoping Review, of Reviews","volume":"8","author":"Negash Bekelu","year":"2023","unstructured":"Bekelu Negash, Alan Katz, Christine J. Neilson, Moniruzzaman Moni, Marcello Nesca, Alexander Singer, and Jennifer E. Enns. 2023. De-Identification of Free Text Data, Containing Personal Health Information: A Scoping Review, of Reviews. International Journal of Population Data Science (IJPDS), Vol. 8, 1 (Dec. 2023).","journal-title":"International Journal of Population Data Science (IJPDS)"},{"key":"e_1_2_1_53_1","volume-title":"Conference on Empirical Methods, in Natural Language Processing (EMNLP). 6203-6209","author":"Ning Qiang","year":"2019","unstructured":"Qiang Ning, Sanjay Subramanian, and Dan Roth. 2019. An Improved Neural Baseline, for Temporal Relation Extraction. In Conference on Empirical Methods, in Natural Language Processing (EMNLP). 6203-6209."},{"key":"e_1_2_1_54_1","unstructured":"OpenAI. 2025. Introducing GPT-5. https:\/\/openai.com\/index\/introducing-gpt-5\/"},{"key":"e_1_2_1_55_1","volume-title":"Conference of the Asia-Pacific Chapter, of the Association, for Computational Linguistics, and the Joint Conference, on Natural Language Processing (AACL-IJCNLP). 217-229","author":"Papadopoulou Anthi","year":"2022","unstructured":"Anthi Papadopoulou, Yunhao Yu, Pierre Lison, and Lilja \u00d8vrelid. 2022. Neural Text Sanitization, with Explicit Measures, of Privacy Risk. In Conference of the Asia-Pacific Chapter, of the Association, for Computational Linguistics, and the Joint Conference, on Natural Language Processing (AACL-IJCNLP). 217-229."},{"key":"e_1_2_1_56_1","volume-title":"ACM International Conference, on Management, of Data (SIGMOD, ).","author":"Papenbrock Thorsten","year":"2016","unstructured":"Thorsten Papenbrock and Felix Naumann. 2016. A Hybrid Approach to Functional Dependency Discovery. In ACM International Conference, on Management, of Data (SIGMOD, )."},{"key":"e_1_2_1_57_1","volume-title":"Annual Meeting, of the Association, for Computational Linguistics (ACL). 311-318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: A Method, for Automatic Evaluation, of Machine Translation. In Annual Meeting, of the Association, for Computational Linguistics (ACL). 311-318."},{"key":"e_1_2_1_58_1","first-page":"4","article-title":"The Text Anonymization Benchmark (TAB, ): A Dedicated Corpus, and Evaluation Framework, for Text Anonymization","volume":"48","author":"Pil\u00e1n Ildik\u00f3","year":"2022","unstructured":"Ildik\u00f3 Pil\u00e1n, Pierre Lison, Lilja \u00d8vrelid, Anthi Papadopoulou, David S\u00e1nchez, and Montserrat Batet. 2022. The Text Anonymization Benchmark (TAB, ): A Dedicated Corpus, and Evaluation Framework, for Text Anonymization. Computational Linguistics, Vol. 48, 4 (Dec. 2022), 1053-1101.","journal-title":"Computational Linguistics"},{"key":"e_1_2_1_59_1","first-page":"1","article-title":"Exploring the Limits, of Transfer Learning, with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the Limits, of Transfer Learning, with a Unified Text-to-Text Transformer. Journal of Machine Learning Research (JMLR), Vol. 21, 140 (2020), 1-67.","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"e_1_2_1_60_1","volume-title":"Workshop on Privacy, in Natural Language Processing (PrivateNLP). 123-136","author":"Riabi Arij","year":"2024","unstructured":"Arij Riabi, Menel Mahamdi, Virginie Mouilleron, and Djam\u00e9 Seddah. 2024. Cloaked Classifiers: Pseudonymization Strategies, on Sensitive Classification Tasks. In Workshop on Privacy, in Natural Language Processing (PrivateNLP). 123-136."},{"key":"e_1_2_1_61_1","doi-asserted-by":"crossref","DOI":"10.1109\/69.971193","article-title":". Protecting Respondents Identities in Microdata Release","volume":"13","author":"Samarati P.","year":"2001","unstructured":"P. Samarati. Nov.-Dec.\/2001. Protecting Respondents Identities in Microdata Release. IEEE Transactions on Knowledge and Data Engineering (TKDE), Vol. 13, 6 ( Nov.-Dec.\/2001), 1010-1027.","journal-title":"IEEE Transactions on Knowledge and Data Engineering (TKDE)"},{"key":"e_1_2_1_62_1","first-page":"1","article-title":"C-sanitized: A, Privacy Model for Document Redaction and Sanitization","volume":"67","author":"S\u00e1nchez David","year":"2016","unstructured":"David S\u00e1nchez and Montserrat Batet. 2016. C-sanitized: A, Privacy Model for Document Redaction and Sanitization. Journal of the Association for Information Science and Technology, Vol. 67, 1 (Jan. 2016), 148-163.","journal-title":"Journal of the Association for Information Science and Technology"},{"key":"e_1_2_1_63_1","first-page":"23","volume-title":"Engineering Applications of Artificial Intelligence","volume":"59","author":"S\u00e1nchez David","year":"2017","unstructured":"David S\u00e1nchez and Montserrat Batet. 2017. Toward Sensitive Document Release with Privacy Guarantees. Engineering Applications of Artificial Intelligence, Vol. 59 (March 2017), 23-34."},{"key":"e_1_2_1_64_1","unstructured":"Hao Shen Zhouhong Gu Haokai Hong and Weili Han. 2025. PII-Bench: Evaluating Query-Aware Privacy Protection Systems. arXiv:2502.18545 [cs] http:\/\/arxiv.org\/abs\/2502.18545"},{"key":"e_1_2_1_65_1","unstructured":"spaCy Developers. 2025. spaCy $cdot$ Industrial-strength Natural Language Processing in Python. https:\/\/spacy.io\/"},{"key":"e_1_2_1_66_1","volume-title":"IEEE Symposium, on Security, and Privacy (SP). 4733-4752","author":"Staab Robin","year":"2024","unstructured":"Robin Staab, Nikola Jovanovi\u0107, Mislav Balunovi\u0107, and Martin Vechev. 2024a. From Principle, to Practice: Vertical Data Minimization, for Machine Learning. In IEEE Symposium, on Security, and Privacy (SP). 4733-4752."},{"key":"e_1_2_1_67_1","volume-title":"International Conference, on Learning Representations (ICLR, ).","author":"Staab Robin","year":"2024","unstructured":"Robin Staab, Mark Vero, Mislav Balunovic, and Martin Vechev. 2024b. Beyond Memorization: Violating Privacy, via Inference, with Large Language Models. In International Conference, on Learning Representations (ICLR, )."},{"key":"e_1_2_1_68_1","volume-title":"Are Advanced Anonymizers. In International Conference, on Learning Representations (ICLR, ). arXiv:2402","author":"Staab Robin","year":"2025","unstructured":"Robin Staab, Mark Vero, Mislav Balunovi\u0107, and Martin Vechev. 2025. Large Language Models, Are Advanced Anonymizers. In International Conference, on Learning Representations (ICLR, ). arXiv:2402.13846 [cs]"},{"key":"e_1_2_1_69_1","volume-title":"USENIX Security Symposium (Security). 1451-1468","author":"Stadler Theresa","year":"2022","unstructured":"Theresa Stadler, Bristena Oprisanu, and Carmela Troncoso. 2022. Synthetic Data, - Anonymisation Groundhog Day. In USENIX Security Symposium (Security). 1451-1468."},{"key":"e_1_2_1_70_1","volume-title":"Training Corpora: An Analysis. In Workshop on Trustworthy Natural Language Processing (TrustNLP). 208-220","author":"Subramani Nishant","year":"2023","unstructured":"Nishant Subramani, Sasha Luccioni, Jesse Dodge, and Margaret Mitchell. 2023. Detecting Personal Information, in Training Corpora: An Analysis. In Workshop on Trustworthy Natural Language Processing (TrustNLP). 208-220."},{"key":"e_1_2_1_71_1","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1142\/S0218488502001648","article-title":"K-Anonymity: A, Model for Protecting Privacy","volume":"10","author":"Sweeney Latanya","year":"2002","unstructured":"Latanya Sweeney. 2002. K-Anonymity: A, Model for Protecting Privacy. International Journal on Uncertainty, Fuzziness and Knowledge-based Systems (IJUFKS), Vol. 10, 05 (2002), 557-570.","journal-title":"International Journal on Uncertainty, Fuzziness and Knowledge-based Systems (IJUFKS)"},{"key":"e_1_2_1_72_1","volume-title":"Joint International Conference, on Computational Linguistics, Language Resources, and Evaluation (LREC-COLING). 13303-13314","author":"Szawerna Maria Irena","year":"2024","unstructured":"Maria Irena Szawerna, Simon Dobnik, Therese Lindstr\u00f6m Tiedemann, Ricardo Mu noz S\u00e1nchez, Xuan-Son Vu, and Elena Volodina. 2024. Pseudonymization Categories, across Domain Boundaries. In Joint International Conference, on Computational Linguistics, Language Resources, and Evaluation (LREC-COLING). 13303-13314."},{"key":"e_1_2_1_73_1","volume-title":"Has Been Turned into a Social Media Surveillance Assistant. Forbes (Nov","author":"Brewster Thomas","year":"2023","unstructured":"Thomas Brewster. 2023. ChatGPT, Has Been Turned into a Social Media Surveillance Assistant. Forbes (Nov. 2023)."},{"key":"e_1_2_1_74_1","volume-title":"States Congress. 1996","author":"United","year":"1996","unstructured":"United States Congress. 1996. Health Insurance Portability and Accountability Act of 1996. https:\/\/www.congress.gov\/bill\/104th-congress\/house-bill\/3103"},{"key":"e_1_2_1_75_1","volume-title":"Findings of the","author":"Utpala Saiteja","unstructured":"Saiteja Utpala, Sara Hooker, and Pin-Yu Chen. 2023. Locally Differentially Private Document Generation Using Zero Shot Prompting. In Findings of the Association, for Computational Linguistics (EMNLP). 8442-8457."},{"key":"e_1_2_1_76_1","volume-title":"Market Structure, and Equilibrium","author":"von Stackelberg Heinrich","unstructured":"Heinrich von Stackelberg. 2010. Market Structure, and Equilibrium. Springer."},{"key":"e_1_2_1_77_1","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1162\/tacl_a_00290","article-title":"Neural Network Acceptability Judgments","volume":"7","author":"Warstadt Alex","year":"2019","unstructured":"Alex Warstadt, Amanpreet Singh, and Samuel R. Bowman. 2019. Neural Network Acceptability Judgments. Transactions of the Association for Computational Linguistics (TACL), Vol. 7 (2019), 625-641.","journal-title":"Transactions of the Association for Computational Linguistics (TACL)"},{"key":"e_1_2_1_78_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv Chujie Zheng Dayiheng Liu Fan Zhou Fei Huang Feng Hu Hao Ge Haoran Wei Huan Lin Jialong Tang Jian Yang Jianhong Tu Jianwei Zhang Jianxin Yang Jiaxi Yang Jing Zhou Jingren Zhou Junyang Lin Kai Dang Keqin Bao Kexin Yang Le Yu Lianghao Deng Mei Li Mingfeng Xue Mingze Li Pei Zhang Peng Wang Qin Zhu Rui Men Ruize Gao Shixuan Liu Shuang Luo Tianhao Li Tianyi Tang Wenbiao Yin Xingzhang Ren Xinyu Wang Xinyu Zhang Xuancheng Ren Yang Fan Yang Su Yichang Zhang Yinger Zhang Yu Wan Yuqiong Liu Zekun Wang Zeyu Cui Zhenru Zhang Zhipeng Zhou and Zihan Qiu. 2025. Qwen3 Technical Report. https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"e_1_2_1_79_1","article-title":"Automatic Detection of Protected Health Information from Clinic Narratives","volume":"58","author":"Yang Hui","year":"2015","unstructured":"Hui Yang and Jonathan M. Garibaldi. 2015. Automatic Detection of Protected Health Information from Clinic Narratives. Journal of Biomedical Informatics (JBI), Vol. 58 (Dec. 2015), S30-S38.","journal-title":"Journal of Biomedical Informatics (JBI)"},{"key":"e_1_2_1_80_1","volume-title":"of De-Identification Techniques, and Their Standardization Directions. IEICE Transactions on Information and Systems (TransInf)","author":"Youm Heung Youl","year":"2020","unstructured":"Heung Youl Youm. 2020. An Overview, of De-Identification Techniques, and Their Standardization Directions. IEICE Transactions on Information and Systems (TransInf), Vol. E103.D, 7 (2020), 1448-1461."},{"key":"e_1_2_1_81_1","volume-title":"Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe. In Annual Meeting, of the Association, for Computational Linguistics (ACL). 1321-1342","author":"Yue Xiang","year":"2023","unstructured":"Xiang Yue, Huseyin Inan, Xuechen Li, Girish Kumar, Julia McAnallen, Hoda Shajari, Huan Sun, David Levitan, and Robert Sim. 2023. Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe. In Annual Meeting, of the Association, for Computational Linguistics (ACL). 1321-1342."},{"key":"e_1_2_1_82_1","volume-title":"Conference on Neural Information Processing Systems (NeurIPS, ).","author":"Yukhymenko Hanna","year":"2024","unstructured":"Hanna Yukhymenko, Robin Staab, Mark Vero, and Martin Vechev. 2024. A Synthetic Dataset, for Personal Attribute Inference. In Conference on Neural Information Processing Systems (NeurIPS, )."},{"key":"e_1_2_1_83_1","volume-title":"International Conference, on Learning Representations (ICLR, ).","author":"Zhang Tianyi","year":"2020","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation, with BERT. In International Conference, on Learning Representations (ICLR, )."}],"container-title":["Proceedings of the ACM on Management of Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3802109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T18:19:29Z","timestamp":1779128369000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3802109"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":83,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5,18]]}},"alternative-id":["10.1145\/3802109"],"URL":"https:\/\/doi.org\/10.1145\/3802109","relation":{},"ISSN":["2836-6573"],"issn-type":[{"value":"2836-6573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,18]]}}}