{"id":"https://openalex.org/W7167905372","doi":"https://doi.org/10.1145/3805712.3809572","title":"How Far Are We from Automatically Identifying Violations of the Data Minimization Principle in Privacy Policies?","display_name":"How Far Are We from Automatically Identifying Violations of the Data Minimization Principle in Privacy Policies?","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167905372","doi":"https://doi.org/10.1145/3805712.3809572"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809572","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809572","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809572","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139869445","display_name":"Zhou Z","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyan Zhou","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-9143-8385","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693510","display_name":"Yanru He","orcid":"https://orcid.org/0000-0001-9546-5043"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanru He","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and State Key Laboratory of Cyberspace Security Defense, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9546-5043","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and State Key Laboratory of Cyberspace Security Defense, Beijing, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100655346","display_name":"Yunchuan Guo","orcid":"https://orcid.org/0000-0002-9611-5368"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunchuan Guo","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9611-5368","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140408618","display_name":"Haoyang Yu","orcid":"https://orcid.org/0009-0003-4428-5108"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyang Yu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-4428-5108","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140445301","display_name":"Liang Fang","orcid":"https://orcid.org/0009-0007-6448-5720"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Fang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and State Key Laboratory of Cyberspace Security Defense, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-6448-5720","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and State Key Laboratory of Cyberspace Security Defense, Beijing, China","institution_ids":["https://openalex.org/I4210156404"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100325259","display_name":"Fenghua Li","orcid":"https://orcid.org/0000-0003-0638-5610"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fenghua Li","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0638-5610","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China, School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China, and State Key Laboratory of Cyberspace Security Defense, Beijing, China","institution_ids":["https://openalex.org/I4210156404"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210156404"],"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":"2556","last_page":"2566"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11045","display_name":"Privacy, Security, and Data Protection","score":0.7149999737739563,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11045","display_name":"Privacy, Security, and Data Protection","score":0.7149999737739563,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.057100001722574234,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.04320000112056732,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.6590999960899353},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.6424000263214111},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5760999917984009},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.48910000920295715},{"id":"https://openalex.org/keywords/service-provider","display_name":"Service provider","score":0.44110000133514404},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.4262000024318695},{"id":"https://openalex.org/keywords/personally-identifiable-information","display_name":"Personally identifiable information","score":0.4081000089645386},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3763999938964844},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.36739999055862427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573000192642212},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.6590999960899353},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.6424000263214111},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5760999917984009},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.48910000920295715},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48179998993873596},{"id":"https://openalex.org/C116537","wikidata":"https://www.wikidata.org/wiki/Q2169973","display_name":"Service provider","level":3,"score":0.44110000133514404},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C169093310","wikidata":"https://www.wikidata.org/wiki/Q3702971","display_name":"Personally identifiable information","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.36739999055862427},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3458000123500824},{"id":"https://openalex.org/C69360830","wikidata":"https://www.wikidata.org/wiki/Q1172237","display_name":"Data Protection Act 1998","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C193934123","wikidata":"https://www.wikidata.org/wiki/Q7246028","display_name":"Privacy by Design","level":3,"score":0.33959999680519104},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C509729295","wikidata":"https://www.wikidata.org/wiki/Q7246032","display_name":"Privacy software","level":3,"score":0.32100000977516174},{"id":"https://openalex.org/C49895821","wikidata":"https://www.wikidata.org/wiki/Q5227368","display_name":"Data verification","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C165609540","wikidata":"https://www.wikidata.org/wiki/Q1172486","display_name":"Data breach","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2754000127315521},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809572","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809572","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809572","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809572","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7183703780174255,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2740765036","https://openalex.org/W2921026077","https://openalex.org/W2962909572","https://openalex.org/W2999830435","https://openalex.org/W3035707807","https://openalex.org/W3214522776","https://openalex.org/W4317898419","https://openalex.org/W4384345690","https://openalex.org/W4385522472","https://openalex.org/W4386907303","https://openalex.org/W4388958893","https://openalex.org/W4389984066","https://openalex.org/W4391591467","https://openalex.org/W4391876619","https://openalex.org/W4394745587","https://openalex.org/W4400681521","https://openalex.org/W4401808240","https://openalex.org/W4401857375","https://openalex.org/W4402667093","https://openalex.org/W4402671258","https://openalex.org/W4404534210","https://openalex.org/W4404782319","https://openalex.org/W4404782513","https://openalex.org/W4404783449","https://openalex.org/W4406604560","https://openalex.org/W4411549886","https://openalex.org/W4416016556","https://openalex.org/W4416037109","https://openalex.org/W6891862129"],"related_works":[],"abstract_inverted_index":{"Data":[0],"protection":[1],"laws":[2],"and":[3,21,48,64,75,84,122,143,183,198],"regulations":[4],"require":[5],"service":[6,52],"providers":[7],"to":[8,32,43,62,147,173,180],"disclose":[9],"data":[10,28,34,55,82,105,114,162,167,192,206],"practices":[11,29,83,163],"in":[12,66,108,209],"privacy":[13,67,70,109,141,210],"policies,":[14,211],"specifying":[15],"what":[16,23,44],"personal":[17,41],"information":[18,42],"is":[19,45,57],"processed":[20],"for":[22,50,100,151,204],"purposes.":[24,53],"For":[25],"compliance,":[26],"these":[27,90],"must":[30],"adhere":[31],"the":[33,38,51,104,156,166,171],"minimization":[35,56,106,115,168,207],"principle,":[36,169],"limiting":[37],"processing":[39],"of":[40,80,103,196,202],"directly":[46],"relevant":[47],"necessary":[49],"However,":[54],"context-dependent,":[58],"making":[59],"violations":[60,102,116,121,179,208],"difficult":[61],"define":[63],"quantify":[65],"policies.":[68,110],"Meanwhile,":[69],"policies":[71,142],"are":[72],"semantically":[73],"complex":[74],"unstructured,":[76],"hindering":[77],"accurate":[78],"extraction":[79,194],"fine-grained":[81,126],"large-scale":[85,140],"automated":[86],"evaluation.":[87,154],"To":[88],"address":[89],"issues,":[91],"we":[92,130],"propose":[93],"DataMini,":[94],"a":[95,132],"human--LLM":[96,152],"collaborative":[97,153],"evaluation":[98,127,214],"framework":[99,172],"identifying":[101,177,205],"principle":[107],"First,":[111],"DataMini":[112,189],"categorizes":[113],"into":[117],"two":[118],"dimensions:":[119],"inherent":[120],"contextual":[123],"violations,":[124],"establishing":[125],"criteria.":[128],"Second,":[129],"construct":[131],"compliance":[133,149,157],"baseline":[134,158],"by":[135,216],"mining":[136],"high-frequency":[137],"patterns":[138],"from":[139],"integrating":[144],"expert":[145],"knowledge":[146],"derive":[148],"mappings":[150],"Finally,":[155],"can":[159],"automatically":[160],"verify":[161],"that":[164,188],"satisfy":[165],"enabling":[170],"focus":[174],"exclusively":[175],"on":[176],"suspected":[178],"improve":[181],"efficiency":[182],"accuracy.":[184],"Extensive":[185],"evaluations":[186],"demonstrate":[187],"exhibits":[190],"superior":[191],"practice":[193],"accuracy":[195],"83.46%":[197],"achieves":[199],"an":[200],"F1-score":[201],"0.8180":[203],"reducing":[212],"manual":[213],"effort":[215],"approximately":[217],"80%.":[218]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-11T00:00:00"}
