{"id":"https://openalex.org/W4288067960","doi":"https://doi.org/10.3390/fi14080228","title":"Automatic Detection of Sensitive Data Using Transformer- Based Classifiers","display_name":"Automatic Detection of Sensitive Data Using Transformer- Based Classifiers","publication_year":2022,"publication_date":"2022-07-27","ids":{"openalex":"https://openalex.org/W4288067960","doi":"https://doi.org/10.3390/fi14080228"},"language":"en","primary_location":{"id":"doi:10.3390/fi14080228","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi14080228","pdf_url":"https://www.mdpi.com/1999-5903/14/8/228/pdf?version=1658913753","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-5903/14/8/228/pdf?version=1658913753","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047878885","display_name":"Michael Petrolini","orcid":"https://orcid.org/0000-0002-0829-5822"},"institutions":[{"id":"https://openalex.org/I124601658","display_name":"University of Parma","ror":"https://ror.org/02k7wn190","country_code":"IT","type":"education","lineage":["https://openalex.org/I124601658"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Michael Petrolini","raw_affiliation_strings":["Department of Engineering and Architecture, University of Parma, Parco Area delle Scienze 181a, 43124 Parma, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Engineering and Architecture, University of Parma, Parco Area delle Scienze 181a, 43124 Parma, Italy","institution_ids":["https://openalex.org/I124601658"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090205116","display_name":"Stefano Cagnoni","orcid":"https://orcid.org/0000-0003-4669-512X"},"institutions":[{"id":"https://openalex.org/I124601658","display_name":"University of Parma","ror":"https://ror.org/02k7wn190","country_code":"IT","type":"education","lineage":["https://openalex.org/I124601658"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Stefano Cagnoni","raw_affiliation_strings":["Department of Engineering and Architecture, University of Parma, Parco Area delle Scienze 181a, 43124 Parma, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Engineering and Architecture, University of Parma, Parco Area delle Scienze 181a, 43124 Parma, Italy","institution_ids":["https://openalex.org/I124601658"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008131303","display_name":"Monica Mordonini","orcid":"https://orcid.org/0000-0002-5916-9770"},"institutions":[{"id":"https://openalex.org/I124601658","display_name":"University of Parma","ror":"https://ror.org/02k7wn190","country_code":"IT","type":"education","lineage":["https://openalex.org/I124601658"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Monica Mordonini","raw_affiliation_strings":["Department of Engineering and Architecture, University of Parma, Parco Area delle Scienze 181a, 43124 Parma, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Engineering and Architecture, University of Parma, Parco Area delle Scienze 181a, 43124 Parma, Italy","institution_ids":["https://openalex.org/I124601658"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090205116"],"corresponding_institution_ids":["https://openalex.org/I124601658"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.666,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86378542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"14","issue":"8","first_page":"228","last_page":"228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9908999800682068,"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"}},"topics":[{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9908999800682068,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.9878000020980835,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9850999712944031,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/general-data-protection-regulation","display_name":"General Data Protection Regulation","score":0.8152424097061157},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7850167751312256},{"id":"https://openalex.org/keywords/data-protection-act-1998","display_name":"Data Protection Act 1998","score":0.6601593494415283},{"id":"https://openalex.org/keywords/legislation","display_name":"Legislation","score":0.6366754770278931},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5055828094482422},{"id":"https://openalex.org/keywords/european-union","display_name":"European union","score":0.48973655700683594},{"id":"https://openalex.org/keywords/possession","display_name":"Possession (linguistics)","score":0.45717766880989075},{"id":"https://openalex.org/keywords/data-protection-directive","display_name":"Data Protection Directive","score":0.4258017838001251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3976263403892517},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.3553677797317505},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.34327399730682373},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3430306911468506},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.17249515652656555},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.13624054193496704},{"id":"https://openalex.org/keywords/european-union-law","display_name":"European Union law","score":0.10624659061431885},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.10609972476959229}],"concepts":[{"id":"https://openalex.org/C3090818","wikidata":"https://www.wikidata.org/wiki/Q1172506","display_name":"General Data Protection Regulation","level":3,"score":0.8152424097061157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850167751312256},{"id":"https://openalex.org/C69360830","wikidata":"https://www.wikidata.org/wiki/Q1172237","display_name":"Data Protection Act 1998","level":2,"score":0.6601593494415283},{"id":"https://openalex.org/C2777351106","wikidata":"https://www.wikidata.org/wiki/Q49371","display_name":"Legislation","level":2,"score":0.6366754770278931},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5055828094482422},{"id":"https://openalex.org/C2910001868","wikidata":"https://www.wikidata.org/wiki/Q458","display_name":"European union","level":2,"score":0.48973655700683594},{"id":"https://openalex.org/C2780193096","wikidata":"https://www.wikidata.org/wiki/Q3543662","display_name":"Possession (linguistics)","level":2,"score":0.45717766880989075},{"id":"https://openalex.org/C52487910","wikidata":"https://www.wikidata.org/wiki/Q911488","display_name":"Data Protection Directive","level":4,"score":0.4258017838001251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3976263403892517},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.3553677797317505},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.34327399730682373},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3430306911468506},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.17249515652656555},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.13624054193496704},{"id":"https://openalex.org/C115314567","wikidata":"https://www.wikidata.org/wiki/Q208202","display_name":"European Union law","level":3,"score":0.10624659061431885},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.10609972476959229},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C105639569","wikidata":"https://www.wikidata.org/wiki/Q582577","display_name":"Economic policy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/fi14080228","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi14080228","pdf_url":"https://www.mdpi.com/1999-5903/14/8/228/pdf?version=1658913753","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:gam:jftint:v:14:y:2022:i:8:p:228-:d:872831","is_oa":false,"landing_page_url":"https://www.mdpi.com/1999-5903/14/8/228/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:ebeb72ac5df84d9b9e815d0a7b3f81a7","is_oa":true,"landing_page_url":"https://doaj.org/article/ebeb72ac5df84d9b9e815d0a7b3f81a7","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Future Internet, Vol 14, Iss 8, p 228 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1999-5903/14/8/228/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/fi14080228","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Future Internet; Volume 14; Issue 8; Pages: 228","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/fi14080228","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi14080228","pdf_url":"https://www.mdpi.com/1999-5903/14/8/228/pdf?version=1658913753","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4288067960.pdf","grobid_xml":"https://content.openalex.org/works/W4288067960.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W1873763122","https://openalex.org/W2096707493","https://openalex.org/W2116027179","https://openalex.org/W2123820077","https://openalex.org/W2164778205","https://openalex.org/W2194775991","https://openalex.org/W2548173722","https://openalex.org/W2906512717","https://openalex.org/W2962739339","https://openalex.org/W2980271516","https://openalex.org/W3005641657","https://openalex.org/W3011574394","https://openalex.org/W3088409176","https://openalex.org/W3125356411","https://openalex.org/W3179937365","https://openalex.org/W3184248340","https://openalex.org/W3214053215","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2901967497","https://openalex.org/W2789497412","https://openalex.org/W2910484607","https://openalex.org/W2981440830","https://openalex.org/W3171079982","https://openalex.org/W2810958358","https://openalex.org/W2087147177","https://openalex.org/W4362572846","https://openalex.org/W2047896827","https://openalex.org/W2566134098"],"abstract_inverted_index":{"The":[0,183],"General":[1],"Data":[2],"Protection":[3],"Regulation":[4],"(GDPR)":[5],"has":[6],"allowed":[7],"EU":[8],"citizens":[9],"and":[10,27,29,56,75,132,142],"residents":[11,46],"to":[12,116,164,193,203,213,222,239,251,265,287],"have":[13,240,285],"more":[14],"control":[15],"over":[16],"their":[17,57],"personal":[18],"data,":[19,95],"simplifying":[20],"the":[21,34,49,73,79,82,117,124,176,186,199,220,224,245,253,279,289],"regulatory":[22],"environment":[23],"affecting":[24],"international":[25],"business":[26],"unifying":[28],"homogenising":[30],"privacy":[31],"legislation":[32],"within":[33,147],"EU.":[35],"This":[36],"regulation":[37],"affects":[38],"all":[39],"companies":[40,69],"that":[41,96,210],"process":[42],"data":[43,66,83,114,129,138,174,246,267,282],"of":[44,48,65,78,81,123,137,172,178,185,207,227,244,268],"European":[45],"regardless":[47],"place":[50],"in":[51,170,189,197,234,256,273],"which":[52,231],"they":[53,84,91,145,232,247],"are":[54,92,139,211],"processed":[55],"registered":[58],"office,":[59],"providing":[60],"for":[61,236],"a":[62,148,155,158,167,237,241,261,274],"strict":[63],"discipline":[64],"protection.":[67],"These":[68,135],"must":[70],"comply":[71],"with":[72,230],"GDPR":[74],"be":[76],"aware":[77],"content":[80],"manage;":[85],"this":[86,190,257],"is":[87,161,169,192],"especially":[88],"important":[89],"if":[90,166],"holding":[93],"sensitive":[94,173,215,228],"is,":[97],"any":[98],"information":[99],"regarding":[100],"racial":[101],"or":[102,108,120,157,271],"ethnic":[103],"origin,":[104],"political":[105],"opinions,":[106],"religious":[107],"philosophical":[109],"beliefs,":[110],"trade":[111],"union":[112],"membership,":[113],"relating":[115],"sexual":[118,121],"life":[119],"orientation":[122],"person,":[125],"as":[126,128,151,260],"well":[127],"on":[130,278],"physical":[131],"mental":[133],"health.":[134],"classes":[136],"hardly":[140],"structured,":[141],"most":[143],"frequently":[144],"appear":[146],"document":[149],"such":[150],"an":[152],"email":[153],"message,":[154],"review":[156],"post.":[159],"It":[160],"extremely":[162],"difficult":[163],"know":[165],"company":[168,238],"possession":[171],"at":[175],"risk":[177],"not":[179],"protecting":[180],"them":[181],"properly.":[182],"goal":[184],"study":[187],"described":[188,255],"paper":[191,258],"use":[194],"Machine":[195],"Learning,":[196],"particular":[198,225],"Transformer":[200],"deep-learning":[201],"model,":[202],"develop":[204],"classifiers":[205,221],"capable":[206],"detecting":[208],"documents":[209],"likely":[212],"include":[214],"data.":[216],"Additionally,":[217],"we":[218,284],"want":[219],"recognize":[223],"type":[226],"topic":[229],"deal,":[233],"order":[235],"better":[242],"knowledge":[243],"own.":[248],"We":[249],"expect":[250],"make":[252],"model":[254],"available":[259,281],"web":[262],"service,":[263],"customized":[264],"private":[266],"possible":[269],"customers,":[270],"even":[272],"free-to-use":[275],"version":[276],"based":[277],"freely":[280],"set":[283],"built":[286],"train":[288],"classifiers.":[290]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2022-07-28T00:00:00"}
