{"id":"https://openalex.org/W4392904073","doi":"https://doi.org/10.1109/icassp48485.2024.10448234","title":"Recovering from Privacy-Preserving Masking with Large Language Models","display_name":"Recovering from Privacy-Preserving Masking with Large Language Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904073","doi":"https://doi.org/10.1109/icassp48485.2024.10448234"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5087553754","display_name":"Arpita Vats","orcid":null},"institutions":[{"id":"https://openalex.org/I16269868","display_name":"Santa Clara University","ror":"https://ror.org/03ypqe447","country_code":"US","type":"education","lineage":["https://openalex.org/I16269868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arpita Vats","raw_affiliation_strings":["Santa Clara University,Santa Clara,CA","Santa Clara University, Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Santa Clara University,Santa Clara,CA","institution_ids":["https://openalex.org/I16269868"]},{"raw_affiliation_string":"Santa Clara University, Santa Clara, CA","institution_ids":["https://openalex.org/I16269868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462347","display_name":"Zhe Liu","orcid":"https://orcid.org/0000-0001-8578-2635"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Liu","raw_affiliation_strings":["Meta,Menlo Park,CA","Meta, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta,Menlo Park,CA","institution_ids":["https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Meta, Menlo Park, CA","institution_ids":["https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101679135","display_name":"Su Peng","orcid":"https://orcid.org/0000-0002-3073-5695"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peng Su","raw_affiliation_strings":["Meta,Menlo Park,CA","Meta, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta,Menlo Park,CA","institution_ids":["https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Meta, Menlo Park, CA","institution_ids":["https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075310174","display_name":"Debjyoti Paul","orcid":"https://orcid.org/0000-0001-8057-399X"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Debjyoti Paul","raw_affiliation_strings":["Meta,Menlo Park,CA","Meta, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta,Menlo Park,CA","institution_ids":["https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Meta, Menlo Park, CA","institution_ids":["https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103207430","display_name":"Yingyi Ma","orcid":"https://orcid.org/0000-0002-0205-0197"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingyi Ma","raw_affiliation_strings":["Meta,Menlo Park,CA","Meta, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta,Menlo Park,CA","institution_ids":["https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Meta, Menlo Park, CA","institution_ids":["https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101846108","display_name":"Yutong Pang","orcid":"https://orcid.org/0000-0003-4829-4741"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yutong Pang","raw_affiliation_strings":["Meta,Menlo Park,CA","Meta, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta,Menlo Park,CA","institution_ids":["https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Meta, Menlo Park, CA","institution_ids":["https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101468572","display_name":"Zeeshan Ahmed","orcid":"https://orcid.org/0009-0005-8514-9625"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeeshan Ahmed","raw_affiliation_strings":["Meta,Menlo Park,CA","Meta, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta,Menlo Park,CA","institution_ids":["https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Meta, Menlo Park, CA","institution_ids":["https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066166549","display_name":"Ozlem Kalinli","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ozlem Kalinli","raw_affiliation_strings":["Meta,Menlo Park,CA","Meta, Menlo Park, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta,Menlo Park,CA","institution_ids":["https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Meta, Menlo Park, CA","institution_ids":["https://openalex.org/I4210099336"]}]}],"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":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10771","last_page":"10775"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.995199978351593,"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/T10028","display_name":"Topic Modeling","score":0.995199978351593,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9915000200271606,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9370999932289124,"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/computer-science","display_name":"Computer science","score":0.8733348846435547},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7118983864784241},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.699211061000824},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6467611789703369},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6275607347488403},{"id":"https://openalex.org/keywords/obfuscation","display_name":"Obfuscation","score":0.49540889263153076},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.4756990373134613},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4484736919403076},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.43028807640075684},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.4203239977359772},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40593090653419495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40200093388557434},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.383569598197937},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35412198305130005},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3177838623523712},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16336694359779358},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15670043230056763}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8733348846435547},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7118983864784241},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.699211061000824},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6467611789703369},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6275607347488403},{"id":"https://openalex.org/C40305131","wikidata":"https://www.wikidata.org/wiki/Q2616305","display_name":"Obfuscation","level":2,"score":0.49540889263153076},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.4756990373134613},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4484736919403076},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.43028807640075684},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.4203239977359772},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40593090653419495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40200093388557434},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.383569598197937},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35412198305130005},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3177838623523712},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16336694359779358},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15670043230056763},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.47999998927116394,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1494108583","https://openalex.org/W1494198834","https://openalex.org/W2026149468","https://openalex.org/W2051267297","https://openalex.org/W2090336914","https://openalex.org/W2144578941","https://openalex.org/W2752929869","https://openalex.org/W2896457183","https://openalex.org/W2943845043","https://openalex.org/W2952604841","https://openalex.org/W2963240019","https://openalex.org/W2965373594","https://openalex.org/W2982456909","https://openalex.org/W3002330681","https://openalex.org/W3010607409","https://openalex.org/W3037225795","https://openalex.org/W3162665866","https://openalex.org/W3168867926","https://openalex.org/W3175115403","https://openalex.org/W3206965164","https://openalex.org/W4221159672","https://openalex.org/W4281262808","https://openalex.org/W4297841692","https://openalex.org/W4298422451","https://openalex.org/W4306705033","https://openalex.org/W4384918448","https://openalex.org/W4385571923","https://openalex.org/W4385823096","https://openalex.org/W6603931906","https://openalex.org/W6727099177","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6763393573","https://openalex.org/W6766673545","https://openalex.org/W6769802879","https://openalex.org/W6776169701","https://openalex.org/W6787335730","https://openalex.org/W6796581206","https://openalex.org/W6803334173","https://openalex.org/W6810332117","https://openalex.org/W6845828557","https://openalex.org/W6854866820"],"related_works":["https://openalex.org/W4224216661","https://openalex.org/W2132360941","https://openalex.org/W3210347767","https://openalex.org/W2066014542","https://openalex.org/W67940504","https://openalex.org/W2024170198","https://openalex.org/W2152144666","https://openalex.org/W1819617256","https://openalex.org/W2596984206","https://openalex.org/W1507511632"],"abstract_inverted_index":{"Model":[0],"adaptation":[1],"is":[2,25],"crucial":[3],"to":[4,58,66,91,141],"handle":[5],"the":[6,59,124,136,146,150],"discrepancy":[7],"between":[8],"proxy":[9],"training":[10],"data":[11,15,22,73,152],"and":[12,54,97,112,116],"actual":[13],"users\u2019":[14],"received.":[16],"To":[17],"effectively":[18],"perform":[19,117],"adaptation,":[20],"textual":[21,72],"of":[23,62,94,126],"users":[24],"typically":[26],"stored":[27],"on":[28,102,120,135,149],"servers":[29],"or":[30],"their":[31,99],"local":[32],"devices,":[33],"where":[34],"downstream":[35,103],"natural":[36],"language":[37,88,104],"processing":[38],"(NLP)":[39],"models":[40,89,133],"can":[41],"be":[42],"directly":[43],"trained":[44,134,148],"using":[45],"such":[46],"in-domain":[47],"data.":[48],"However,":[49],"this":[50,83],"might":[51],"raise":[52],"privacy":[53],"security":[55],"concerns":[56],"due":[57],"extra":[60],"risks":[61],"exposing":[63],"user":[64],"information":[65,70],"adversaries.":[67],"Replacing":[68],"identifying":[69],"in":[71],"with":[74,145],"a":[75],"generic":[76],"marker":[77],"has":[78],"been":[79],"recently":[80],"explored.":[81],"In":[82],"work,":[84],"we":[85,108],"leverage":[86],"large":[87],"(LLMs)":[90],"suggest":[92],"substitutes":[93],"masked":[95],"tokens":[96],"have":[98],"effectiveness":[100],"evaluated":[101],"modeling":[105],"tasks.":[106],"Specifically,":[107],"propose":[109],"multiple":[110],"pre-trained":[111],"fine-tuned":[113],"LLM-based":[114],"approaches":[115],"empirical":[118],"studies":[119],"various":[121],"datasets":[122],"for":[123],"comparison":[125],"these":[127],"methods.":[128],"Experimental":[129],"results":[130],"show":[131],"that":[132],"obfuscation":[137],"corpora":[138],"are":[139],"able":[140],"achieve":[142],"comparable":[143],"performance":[144],"ones":[147],"original":[151],"without":[153],"privacy-preserving":[154],"token":[155],"masking.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}