{"id":"https://openalex.org/W4403486636","doi":"https://doi.org/10.3233/faia240960","title":"Inside the Black Box: Detecting Data Leakage in Pre-Trained Language Encoders","display_name":"Inside the Black Box: Detecting Data Leakage in Pre-Trained Language Encoders","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403486636","doi":"https://doi.org/10.3233/faia240960"},"language":"en","primary_location":{"id":"doi:10.3233/faia240960","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240960","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240960","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240960","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101823043","display_name":"Xin Yuan","orcid":"https://orcid.org/0000-0001-5293-003X"},"institutions":[{"id":"https://openalex.org/I4210128801","display_name":"Helmholtz Center for Information Security","ror":"https://ror.org/02njgxr09","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210128801"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yuan Xin","raw_affiliation_strings":["CISPA Helmholtz Center for Information Security"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CISPA Helmholtz Center for Information Security","institution_ids":["https://openalex.org/I4210128801"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100415036","display_name":"Zheng Li","orcid":"https://orcid.org/0000-0002-9704-7651"},"institutions":[{"id":"https://openalex.org/I4210128801","display_name":"Helmholtz Center for Information Security","ror":"https://ror.org/02njgxr09","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210128801"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zheng Li","raw_affiliation_strings":["CISPA Helmholtz Center for Information Security"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CISPA Helmholtz Center for Information Security","institution_ids":["https://openalex.org/I4210128801"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029174306","display_name":"Ning Yu","orcid":"https://orcid.org/0000-0001-6084-3630"},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ning Yu","raw_affiliation_strings":["Netflix Eyeline Studios"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netflix Eyeline Studios","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077770549","display_name":"Dingfan Chen","orcid":"https://orcid.org/0000-0001-7279-6624"},"institutions":[{"id":"https://openalex.org/I4210128801","display_name":"Helmholtz Center for Information Security","ror":"https://ror.org/02njgxr09","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210128801"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dingfan Chen","raw_affiliation_strings":["CISPA Helmholtz Center for Information Security"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CISPA Helmholtz Center for Information Security","institution_ids":["https://openalex.org/I4210128801"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003887059","display_name":"Mario Fritz","orcid":"https://orcid.org/0000-0001-8949-9896"},"institutions":[{"id":"https://openalex.org/I4210128801","display_name":"Helmholtz Center for Information Security","ror":"https://ror.org/02njgxr09","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210128801"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mario Fritz","raw_affiliation_strings":["CISPA Helmholtz Center for Information Security"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CISPA Helmholtz Center for Information Security","institution_ids":["https://openalex.org/I4210128801"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102730269","display_name":"Michael Backes","orcid":"https://orcid.org/0000-0002-7130-9211"},"institutions":[{"id":"https://openalex.org/I4210128801","display_name":"Helmholtz Center for Information Security","ror":"https://ror.org/02njgxr09","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210128801"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Backes","raw_affiliation_strings":["CISPA Helmholtz Center for Information Security"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CISPA Helmholtz Center for Information Security","institution_ids":["https://openalex.org/I4210128801"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100354727","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0002-8326-1040"},"institutions":[{"id":"https://openalex.org/I4210128801","display_name":"Helmholtz Center for Information Security","ror":"https://ror.org/02njgxr09","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210128801"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["CISPA Helmholtz Center for Information Security"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CISPA Helmholtz Center for Information Security","institution_ids":["https://openalex.org/I4210128801"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5199,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85464684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"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/T11122","display_name":"Online Learning and Analytics","score":0.8698999881744385,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11122","display_name":"Online Learning and Analytics","score":0.8698999881744385,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.8356000185012817,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.8303999900817871,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/leakage","display_name":"Leakage (economics)","score":0.6724777221679688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.56662917137146},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.5435603857040405},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4640319347381592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36909231543540955},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3631577789783478},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15517336130142212}],"concepts":[{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.6724777221679688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.56662917137146},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5435603857040405},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4640319347381592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36909231543540955},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3631577789783478},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15517336130142212},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia240960","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240960","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240960","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia240960","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240960","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240960","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403486636.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2047881532","https://openalex.org/W2285795935","https://openalex.org/W2384362569","https://openalex.org/W4389072557","https://openalex.org/W2142795561","https://openalex.org/W4319452366","https://openalex.org/W4205302943","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Despite":[0],"being":[1],"prevalent":[2],"in":[3,68,138,143],"the":[4,50,96,99,107,111,140],"general":[5],"field":[6],"of":[7,25,39,53,79,101,110],"Natural":[8],"Language":[9],"Processing":[10],"(NLP),":[11],"pre-trained":[12,44,62,80,145],"language":[13,45,63,146],"models":[14,59],"inherently":[15],"carry":[16],"privacy":[17,118,141],"and":[18,87,130,136],"copyright":[19],"concerns":[20],"due":[21],"to":[22],"their":[23],"nature":[24],"training":[26],"on":[27,49],"large-scale":[28],"web-scraped":[29],"data.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34,126],"pioneer":[35],"a":[36,117],"systematic":[37],"exploration":[38],"such":[40],"risks":[41],"associated":[42],"with":[43],"encoders,":[46],"specifically":[47],"focusing":[48],"membership":[51,102],"leakage":[52,103],"pre-training":[54],"data":[55],"exposed":[56],"through":[57],"downstream":[58,85,112],"adapted":[60],"from":[61],"encoders\u2013an":[64],"aspect":[65],"largely":[66],"overlooked":[67],"existing":[69],"literature.":[70],"Our":[71],"study":[72],"encompasses":[73],"comprehensive":[74],"experiments":[75],"across":[76],"four":[77],"types":[78],"encoder":[81],"architectures,":[82],"three":[83],"representative":[84],"tasks,":[86],"five":[88],"benchmark":[89],"datasets.":[90],"Intriguingly,":[91],"our":[92],"evaluations":[93],"reveal,":[94],"for":[95],"first":[97],"time,":[98],"existence":[100],"even":[104],"when":[105],"only":[106],"black-box":[108],"output":[109],"model":[113],"is":[114],"exposed,":[115],"highlighting":[116],"risk":[119],"far":[120],"greater":[121],"than":[122],"previously":[123],"assumed.":[124],"Alongside,":[125],"present":[127],"in-depth":[128],"analysis":[129],"insights":[131],"toward":[132],"guiding":[133],"future":[134],"researchers":[135],"practitioners":[137],"addressing":[139],"considerations":[142],"developing":[144],"models.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
