{"id":"https://openalex.org/W7124143115","doi":"https://doi.org/10.1109/icpads67057.2025.11323205","title":"SafeSQL-LLM: A Synthetic Data Approach to Privacy-Preserving Text-to-SQL","display_name":"SafeSQL-LLM: A Synthetic Data Approach to Privacy-Preserving Text-to-SQL","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124143115","doi":"https://doi.org/10.1109/icpads67057.2025.11323205"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11323205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055893466","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0002-5206-5434"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University,Hefei,China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101112092","display_name":"Shenghui Zhao","orcid":"https://orcid.org/0000-0002-6793-7709"},"institutions":[{"id":"https://openalex.org/I4210115456","display_name":"Chuzhou University","ror":"https://ror.org/037663q52","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210115456"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenghui Zhao","raw_affiliation_strings":["School of Artificial Intelligence, Chuzhou University,Chuzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Chuzhou University,Chuzhou,China","institution_ids":["https://openalex.org/I4210115456"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.1615000069141388,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.1615000069141388,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11424","display_name":"Security and Verification in Computing","score":0.10559999942779541,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12479","display_name":"Web Application Security Vulnerabilities","score":0.08190000057220459,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.7379999756813049},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.6622999906539917},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4943999946117401},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.4465999901294708},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.40529999136924744},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4047999978065491},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.39469999074935913},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.3774000108242035},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.3637000024318695}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8230999708175659},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.7379999756813049},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6622999906539917},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5443999767303467},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4943999946117401},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.4465999901294708},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3693999946117401},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.3089999854564667},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2624000012874603},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C10511746","wikidata":"https://www.wikidata.org/wiki/Q899388","display_name":"Data security","level":3,"score":0.25679999589920044},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11323205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2622255369","https://openalex.org/W2890431379","https://openalex.org/W2950067395","https://openalex.org/W3093819145","https://openalex.org/W3156729426","https://openalex.org/W4389523781","https://openalex.org/W4391876619","https://openalex.org/W4408529725"],"related_works":[],"abstract_inverted_index":{"Text-to-SQL":[0],"systems":[1],"powered":[2],"by":[3],"large":[4],"language":[5,11],"models":[6,22],"(LLMs)":[7],"enable":[8],"intuitive":[9],"natural":[10],"access":[12],"to":[13,46,63,105],"structured":[14],"databases,":[15],"but":[16],"querying":[17],"sensitive":[18],"tables":[19],"via":[20],"cloud-hosted":[21],"raises":[23],"critical":[24],"privacy":[25,35],"concerns.":[26],"We":[27],"present":[28],"SafeSQLLLM,":[29],"a":[30,43,79,117,180],"hybrid":[31],"framework":[32,142],"that":[33,51,107,115,164],"preserves":[34],"without":[36],"sacrificing":[37],"query":[38],"accuracy.":[39],"Our":[40],"approach":[41],"uses":[42],"local":[44],"LLM":[45],"generate":[47],"synthetic":[48,76,119,154,167],"table":[49,122],"rows":[50,77,131],"statistically":[52],"mimic":[53],"the":[54,71,87,140,144,172],"original":[55],"data":[56,66,110,155,168],"distribution,":[57],"validates":[58],"them":[59],"through":[60],"safety":[61],"checks":[62],"prevent":[64],"real":[65,109,159],"leakage,":[67],"and":[68,74,102,189],"shares":[69],"only":[70,153],"database":[72,177],"schema":[73],"verified":[75],"with":[78,126,139,158],"cloud-based":[80],"model":[81],"for":[82,183],"SQL":[83],"generation.":[84],"Evaluated":[85],"on":[86],"Spider":[88],"benchmark":[89],"[1],":[90],"SafeSQL-LLM":[91],"achieves":[92],"83.1%":[93],"execution":[94],"accuracy-a":[95],"2.8-percentage-point":[96],"improvement":[97],"over":[98],"schema-only":[99],"baselines":[100],"(80.3%)":[101],"comparable":[103],"performance":[104,128],"methods":[106],"expose":[108],"(84.4%).":[111],"Ablation":[112],"studies":[113],"reveal":[114],"even":[116],"single":[118],"row":[120],"per":[121],"yields":[123],"significant":[124],"gains,":[125],"optimal":[127],"using":[129,152],"3-5":[130],"before":[132],"diminishing":[133],"returns":[134],"set":[135],"in.":[136],"Furthermore,":[137],"integration":[138],"DEA-SQL":[141],"demonstrates":[143],"generalizability":[145],"of":[146],"our":[147],"approach,":[148],"maintaining":[149],"83.6%":[150],"accuracy":[151],"versus":[156],"85.6%":[157],"data.":[160],"These":[161],"results":[162],"establish":[163],"locally":[165],"generated":[166],"can":[169],"effectively":[170],"bridge":[171],"privacy-utility":[173],"gap":[174],"in":[175],"LLM-based":[176],"querying,":[178],"offering":[179],"practical":[181],"solution":[182],"privacy-sensitive":[184],"domains":[185],"such":[186],"as":[187],"healthcare":[188],"finance.":[190]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-15T00:00:00"}