{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T22:52:59Z","timestamp":1768517579023,"version":"3.49.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,14]]},"DOI":"10.1109\/icpads67057.2025.11323205","type":"proceedings-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:36:54Z","timestamp":1768423014000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["SafeSQL-LLM: A Synthetic Data Approach to Privacy-Preserving Text-to-SQL"],"prefix":"10.1109","author":[{"given":"Rui","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Anhui University,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenghui","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Chuzhou University,Chuzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"3911","DOI":"10.18653\/v1\/D18-1425","article-title":"Spider: A large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-sql task","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.","author":"Yu","year":"2018"},{"key":"ref2","article-title":"Defining cohorts","volume-title":"CRAN vignette for the R package TreatmentPatterns","year":"2025"},{"key":"ref3","first-page":"589","article-title":"Characterizing basic and complex usage of i2b2 at an academic medical center","volume-title":"AMIA Joint Summits on Translational Science Proceedings","author":"Sholle","year":"2020"},{"issue":"5","key":"ref4","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1007\/s00778-019-00567-8","article-title":"A comparative survey of recent natural language interfaces for databases","volume":"28","author":"Affolter","year":"2019","journal-title":"The VLDB Journal"},{"key":"ref5","volume-title":"Guidance on hipaa and cloud computing","year":"2022"},{"key":"ref6","volume-title":"On-device language models: A comprehensive review","author":"Xu","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3724420"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icde51399.2021.00220"},{"key":"ref9","first-page":"8413","article-title":"Tabert: Pretraining for joint understanding of textual and tabular data","volume-title":"Proceedings of ACL","author":"Yin","year":"2020"},{"key":"ref10","article-title":"Can 11 m already serve as a database interface? a big bench for large-scale database grounded text-to-sqls","volume-title":"Advances in Neural Information Processing Systems 36 (NeurIPS 2023), Datasets and Benchmarks Track","author":"Li","year":"2023"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2021.naacl-main.105","article-title":"Structure-grounded pretraining for text-to-sql","volume-title":"2022, introduces the Spider-Realistic evaluation set.","author":"Deng"},{"key":"ref12","first-page":"10796","article-title":"Decomposition for enhancing attention: Improving 11 m-based text-to-sql through workflow paradigm","author":"Xie","year":"2024","journal-title":"Findings of ACL"},{"key":"ref13","volume-title":"Din-sql: Decomposed in-context learning of text-to-sql with self-correction","author":"Pourreza","year":"2023"},{"key":"ref14","first-page":"664","article-title":"Refsql: A retrieval-augmentation framework for text-to-sql generation","author":"Zhang","year":"2023","journal-title":"Findings of EMNLP"},{"key":"ref15","first-page":"1337","article-title":"Structure-grounded pretraining for text-to-sql","volume-title":"Proceedings of NAACL-HLT","author":"Deng","year":"2021"},{"key":"ref16","volume-title":"Masksql: Safeguarding privacy for llm-based text-to-sql via abstraction","author":"Abedini","year":"2025"},{"key":"ref17","article-title":"Dp-opt: Make large language model your privacy-preserving prompt engineer","volume-title":"iCLR 2024 Spotlight.","author":"Hong","year":"2023"},{"key":"ref18","volume-title":"Privacy-preserving prompt tuning for large language model services","author":"Li","year":"2023"},{"key":"ref19","volume-title":"Language models are realistic tabular data generators","author":"Borisov","year":"2023"},{"key":"ref20","article-title":"Modeling tabular data using conditional GAN","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Xu","year":"2019"},{"key":"ref21","article-title":"The secret sharer: Evaluating and testing unintended memorization in neural networks","volume-title":"28th USENIX Security Symposium","author":"Carlini","year":"2019"},{"key":"ref22","article-title":"Extracting training data from large language models","volume-title":"30th USENIX Security Symposium","author":"Carlini","year":"2021"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.6028\/NIST.IR.8053","article-title":"De-identification of personal information","volume-title":"National Institute of Standards and Technology, Tech. Rep. NISTIR 8053","author":"Garfinkel","year":"2015"},{"key":"ref24","article-title":"PAL: Program-aided language models","volume-title":"International Conference on Machine Learning (ICML)","author":"Gao","year":"2023"},{"key":"ref25","volume-title":"Toolformer: Language models can teach themselves to use tools","author":"Schick","year":"2023"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"1601","DOI":"10.18653\/v1\/2023.emnlp-main.99","article-title":"Evaluating cross-domain text-to-sql models and benchmarks","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Pourreza","year":"2023"},{"key":"ref27","volume-title":"Biomedsql: Text-to-sql for scientific reasoning on biomedical knowledge bases","author":"Koretsky","year":"2025"},{"key":"ref28","volume-title":"Spider evaluation toolkit (official scripts and metrics)","year":"2025"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1162\/tacl_a_00638","article-title":"Lost in the middle: How language models use long contexts","volume":"12","author":"Liu","year":"2024","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref30","volume-title":"Robust text-to-sql generation with execution-guided decoding","author":"Wang","year":"2018"},{"key":"ref31","volume-title":"Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks","author":"Chen","year":"2022"}],"event":{"name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","location":"Hefei, China","start":{"date-parts":[[2025,12,14]]},"end":{"date-parts":[[2025,12,18]]}},"container-title":["2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11322805\/11322871\/11323205.pdf?arnumber=11323205","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:09:53Z","timestamp":1768460993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11323205\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icpads67057.2025.11323205","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]}}}