{"id":"https://openalex.org/W4320024104","doi":"https://doi.org/10.1109/bigdata55660.2022.10020711","title":"Analyzing and Defending against Membership Inference Attacks in Natural Language Processing Classification","display_name":"Analyzing and Defending against Membership Inference Attacks in Natural Language Processing Classification","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4320024104","doi":"https://doi.org/10.1109/bigdata55660.2022.10020711"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020711","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020711","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","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/A5101674028","display_name":"Yijue Wang","orcid":"https://orcid.org/0000-0002-9977-6065"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yijue Wang","raw_affiliation_strings":["University of Connecticut"],"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048064145","display_name":"Nuo Xu","orcid":"https://orcid.org/0000-0001-6148-2830"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nuo Xu","raw_affiliation_strings":["Lehigh University"],"affiliations":[{"raw_affiliation_string":"Lehigh University","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073345631","display_name":"Shaoyi Huang","orcid":"https://orcid.org/0000-0001-6093-9798"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaoyi Huang","raw_affiliation_strings":["University of Connecticut"],"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053352602","display_name":"Kaleel Mahmood","orcid":"https://orcid.org/0000-0002-7672-4449"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaleel Mahmood","raw_affiliation_strings":["University of Connecticut"],"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101596359","display_name":"Dan Guo","orcid":"https://orcid.org/0000-0001-7787-0301"},"institutions":[{"id":"https://openalex.org/I87182695","display_name":"Universidad del Noreste","ror":"https://ror.org/02ahky613","country_code":"MX","type":"education","lineage":["https://openalex.org/I87182695"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Dan Guo","raw_affiliation_strings":["Northeastern University"],"affiliations":[{"raw_affiliation_string":"Northeastern University","institution_ids":["https://openalex.org/I87182695"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030060072","display_name":"Caiwen Ding","orcid":"https://orcid.org/0000-0003-0891-1231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caiwen Ding","raw_affiliation_strings":["University of Connecticut"],"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103129518","display_name":"Wujie Wen","orcid":"https://orcid.org/0000-0003-3440-1905"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wujie Wen","raw_affiliation_strings":["Lehigh University"],"affiliations":[{"raw_affiliation_string":"Lehigh University","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034177039","display_name":"Sanguthevar Rajasekaran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanguthevar Rajasekaran","raw_affiliation_strings":["University of Connecticut"],"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101674028"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3109,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.54127692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9991999864578247,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9991999864578247,"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":0.998199999332428,"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":0.97079998254776,"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/overfitting","display_name":"Overfitting","score":0.8602833151817322},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7459366321563721},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.745159387588501},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6993029713630676},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6796209216117859},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.46892741322517395},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.43986907601356506},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4318464696407318},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4211153984069824},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36983659863471985},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1569981873035431}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8602833151817322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7459366321563721},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.745159387588501},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6993029713630676},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6796209216117859},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.46892741322517395},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.43986907601356506},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4318464696407318},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4211153984069824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36983659863471985},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1569981873035431},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020711","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata55660.2022.10020711","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1574220596","https://openalex.org/W1686810756","https://openalex.org/W2059174629","https://openalex.org/W2109426455","https://openalex.org/W2194775991","https://openalex.org/W2294710185","https://openalex.org/W2473418344","https://openalex.org/W2535690855","https://openalex.org/W2764043458","https://openalex.org/W2795435272","https://openalex.org/W2798657499","https://openalex.org/W2884943453","https://openalex.org/W2911978475","https://openalex.org/W2912023992","https://openalex.org/W2923014074","https://openalex.org/W2930926105","https://openalex.org/W2946363484","https://openalex.org/W2963163009","https://openalex.org/W2963378725","https://openalex.org/W2963674932","https://openalex.org/W2971977646","https://openalex.org/W2976833415","https://openalex.org/W2980658239","https://openalex.org/W2999905431","https://openalex.org/W3035003500","https://openalex.org/W3038012435","https://openalex.org/W3101704102","https://openalex.org/W3103245149","https://openalex.org/W3104136798","https://openalex.org/W3104224589","https://openalex.org/W3171087525","https://openalex.org/W3176659256","https://openalex.org/W3188079459","https://openalex.org/W3205816523","https://openalex.org/W4250106264","https://openalex.org/W4286961857","https://openalex.org/W4293023328","https://openalex.org/W4311165761","https://openalex.org/W4312395015","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6638632666","https://openalex.org/W6739901393","https://openalex.org/W6745148473","https://openalex.org/W6750182894","https://openalex.org/W6763701032","https://openalex.org/W6765055791","https://openalex.org/W6768429542","https://openalex.org/W6775482175","https://openalex.org/W6779101013","https://openalex.org/W6796931752","https://openalex.org/W6801929890"],"related_works":["https://openalex.org/W2989932438","https://openalex.org/W2951851447","https://openalex.org/W3099765033","https://openalex.org/W4362499066","https://openalex.org/W3186919929","https://openalex.org/W4361732492","https://openalex.org/W4287064118","https://openalex.org/W3186840088","https://openalex.org/W2511279186","https://openalex.org/W4320737025"],"abstract_inverted_index":{"The":[0],"risk":[1,43,58],"posed":[2,44],"by":[3,45,172],"Membership":[4],"Inference":[5],"Attack":[6],"(MIA)":[7],"to":[8,47,59,91,179,187,195],"deep":[9],"learning":[10],"models":[11,54,68,88,93,152],"for":[12,86],"Computer":[13,71],"Vision":[14,72],"(CV)":[15,73],"tasks":[16,107],"is":[17],"well":[18],"known,":[19],"but":[20],"MIA":[21,46,154,169,196],"has":[22],"not":[23],"been":[24],"addressed":[25],"or":[26],"explored":[27],"fully":[28],"in":[29,61,80,104,108],"the":[30,41,120,168,180],"Natural":[31],"Language":[32],"Processing":[33],"(NLP)":[34],"domain.":[35],"In":[36,183],"this":[37],"work,":[38],"we":[39,135],"analyze":[40],"security":[42],"NLP":[48,53,87,105,151,208],"models.":[49],"We":[50,96],"show":[51,163],"that":[52,98,118,164],"are":[55,100,214],"at":[56],"great":[57],"MIA,":[60],"some":[62,101],"cases":[63],"even":[64],"more":[65,193],"so":[66],"than":[67],"trained":[69],"on":[70,84,132],"datasets.":[74],"This":[75],"includes":[76],"an":[77],"8.04%":[78],"increase":[79],"attack":[81],"success":[82,170],"rate":[83,171],"average":[85],"(as":[89],"compared":[90,178,186],"CV":[92,128,211],"and":[94,115,124,155,197,209,213],"datasets).":[95],"determine":[97],"there":[99],"unique":[102],"issues":[103],"classification":[106,129],"terms":[109],"of":[110,219],"model":[111,113,222],"overfitting,":[112],"complexity,":[114],"data":[116],"diversity":[117],"make":[119],"privacy":[121],"leakage":[122],"severe":[123],"very":[125],"different":[126,221],"from":[127],"tasks.":[130],"Based":[131],"these":[133],"findings,":[134],"propose":[136],"a":[137,217],"novel":[138],"defense":[139],"algorithm":[140],"-":[141],"Gap":[142],"score":[143],"Regularization":[144],"Integrated":[145],"Pruning":[146],"(GRIP),":[147],"which":[148],"can":[149,166],"protect":[150],"against":[153],"achieve":[156],"competitive":[157],"testing":[158,200],"accuracy.":[159,201],"Our":[160],"experimental":[161,204],"results":[162,205],"GRIP":[165,190],"decrease":[167],"as":[173,175],"much":[174],"31.25%":[176],"when":[177,185],"undefended":[181],"model.":[182],"addition,":[184],"differential":[188],"privacy,":[189],"offers":[191],"7.81%":[192],"robustness":[194],"13.24%":[198],"higher":[199],"Overall":[202],"our":[203],"span":[206],"four":[207],"two":[210],"datasets,":[212],"tested":[215],"with":[216],"total":[218],"five":[220],"architectures.":[223]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}