{"id":"https://openalex.org/W7220753131","doi":null,"title":"Are language models leaking personal information? Memorization vs. Association","display_name":"Are language models leaking personal information? Memorization vs. Association","publication_year":2023,"publication_date":"2023-05-01","ids":{"openalex":"https://openalex.org/W7220753131"},"language":"en","primary_location":{"id":"pmh:oai:www.ideals.illinois.edu:2142/120435","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/2142/120435","pdf_url":"https://www.ideals.illinois.edu/items/127656/bitstreams/427617/data.pdf","source":{"id":"https://openalex.org/S4306401358","display_name":"Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801919071","host_organization_name":"University of Illinois System","host_organization_lineage":["https://openalex.org/I2801919071"],"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":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ideals.illinois.edu/items/127656/bitstreams/427617/data.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102482061","display_name":"Hanyin Shao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shao, Hanyin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5102482061"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9848999977111816,"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":0.9848999977111816,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.008200000040233135,"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/T11045","display_name":"Privacy, Security, and Data Protection","score":0.0038999998942017555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-pre-trained-language-models","display_name":"large pre-trained language models","score":0.8949999809265137},{"id":"https://openalex.org/keywords/privacy-leakage","display_name":"privacy leakage","score":0.9049999713897705},{"id":"https://openalex.org/keywords/memorization","display_name":"memorization","score":0.8629999756813049},{"id":"https://openalex.org/keywords/associations","display_name":"associations","score":0.5630000233650208},{"id":"https://openalex.org/keywords/personal-information","display_name":"personal data","score":0.6539999842643738},{"id":"https://openalex.org/keywords/sensitive-information","display_name":"sensitive data","score":0.3580000102519989},{"id":"https://openalex.org/keywords/privacy-protection","display_name":"privacy preservation","score":0.47600001096725464}],"concepts":[{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.6568999886512756},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.6204000115394592},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.565500020980835},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.4097999930381775},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.398499995470047},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.352400004863739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3467999994754791},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29280000925064087},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.2563999891281128},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:www.ideals.illinois.edu:2142/120435","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/2142/120435","pdf_url":"https://www.ideals.illinois.edu/items/127656/bitstreams/427617/data.pdf","source":{"id":"https://openalex.org/S4306401358","display_name":"Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801919071","host_organization_name":"University of Illinois System","host_organization_lineage":["https://openalex.org/I2801919071"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:www.ideals.illinois.edu:2142/120435","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/2142/120435","pdf_url":"https://www.ideals.illinois.edu/items/127656/bitstreams/427617/data.pdf","source":{"id":"https://openalex.org/S4306401358","display_name":"Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801919071","host_organization_name":"University of Illinois System","host_organization_lineage":["https://openalex.org/I2801919071"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220753131.pdf","grobid_xml":"https://content.openalex.org/works/W7220753131.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W2937845937","https://openalex.org/W2947819652","https://openalex.org/W2950181023","https://openalex.org/W2952604841","https://openalex.org/W2965373594","https://openalex.org/W3001279689","https://openalex.org/W3030163527","https://openalex.org/W3093871960","https://openalex.org/W3118781290","https://openalex.org/W3188505388","https://openalex.org/W3212496002","https://openalex.org/W4220993274","https://openalex.org/W4221159672","https://openalex.org/W4224051134","https://openalex.org/W4283172211","https://openalex.org/W4287888099","https://openalex.org/W4399971973"],"related_works":["https://openalex.org/W7220812376","https://openalex.org/W7220807961","https://openalex.org/W7220816791","https://openalex.org/W7220754004","https://openalex.org/W7220806755","https://openalex.org/W7196968327","https://openalex.org/W7220828632","https://openalex.org/W7220762719","https://openalex.org/W7220794565","https://openalex.org/W7161465197"],"abstract_inverted_index":{"Large":[0],"pre-trained":[1],"language":[2,11],"models":[3,143],"(PLMs)":[4],"have":[5,17],"transformed":[6],"the":[7,19,26,65,93,109,115,129,142,165],"field":[8],"of":[9,29,35,58,108,131,160,167,171],"natural":[10],"processing":[12],"(NLP)":[13],"in":[14,169],"recent":[15,49],"years.PLMs":[16],"become":[18],"basis":[20],"for":[21,101,177],"various":[22],"state-of-the-art":[23],"NLP":[24,36],"systems.Despite":[25],"great":[27,56],"success":[28],"PLMs":[30,53,81,100,120],"solving":[31],"a":[32,55,102],"wide":[33],"range":[34],"tasks,":[37],"there":[38],"is":[39,139],"rising":[40],"concern":[41],"about":[42],"privacy":[43,94,172],"risks":[44],"brought":[45],"with":[46,106,151],"PLMs.For":[47],"example,":[48],"studies":[50],"show":[51],"that":[52,119],"memorize":[54],"portion":[57],"training":[59],"data,":[60],"including":[61],"sensitive":[62],"information,":[63],"while":[64],"information":[66,87,124,134,150],"may":[67],"be":[68],"leaked":[69],"unintentionally":[70],"and":[71,88,180],"utilized":[72],"by":[73,137],"malicious":[74],"adversaries.In":[75],"this":[76],"thesis,":[77],"we":[78,96],"evaluate":[79],"whether":[80],"are":[82,144],"prone":[83],"to":[84,98,127,156,162],"leaking":[85],"personal":[86,123,133,148],"discuss":[89],"possible":[90],"reasons":[91],"behind":[92],"leakage.Specifically,":[95],"attempt":[97],"query":[99],"target":[103],"email":[104,110],"address":[105,111],"contexts":[107],"or":[112],"prompts":[113],"containing":[114],"owner's":[116],"name.We":[117],"find":[118],"do":[121],"leak":[122],"mainly":[125],"due":[126],"memorization.However,":[128],"risk":[130],"specific":[132],"being":[135],"extracted":[136],"attackers":[138],"low":[140],"because":[141],"weak":[145],"at":[146],"associating":[147],"identifying":[149],"its":[152],"owner.We":[153],"also":[154],"try":[155],"quantify":[157],"PLMs'":[158],"capability":[159],"association":[161],"help":[163],"validate":[164],"safety":[166],"PLM":[168],"terms":[170],"preserving.ii":[173],"To":[174],"my":[175],"parents,":[176],"their":[178],"love":[179],"support.":[181]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-07T00:00:00"}