{"id":"https://openalex.org/W4387848684","doi":"https://doi.org/10.1145/3583780.3615019","title":"PSLF: Defending Against Label Leakage in Split Learning","display_name":"PSLF: Defending Against Label Leakage in Split Learning","publication_year":2023,"publication_date":"2023-10-21","ids":{"openalex":"https://openalex.org/W4387848684","doi":"https://doi.org/10.1145/3583780.3615019"},"language":"en","primary_location":{"id":"doi:10.1145/3583780.3615019","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583780.3615019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","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/A5053316484","display_name":"Xiaoqian Wan","orcid":"https://orcid.org/0009-0005-2096-6122"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinwei Wan","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-2096-6122","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424691","display_name":"Jiankai Sun","orcid":"https://orcid.org/0000-0002-7214-0665"},"institutions":[{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiankai Sun","raw_affiliation_strings":["Bytedance Inc., Seattle, USA"],"raw_orcid":"https://orcid.org/0000-0002-7214-0665","affiliations":[{"raw_affiliation_string":"Bytedance Inc., Seattle, USA","institution_ids":["https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042476440","display_name":"Shengjie Wang","orcid":"https://orcid.org/0000-0002-9311-102X"},"institutions":[{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shengjie Wang","raw_affiliation_strings":["Bytedance Inc., Seattle, USA"],"raw_orcid":"https://orcid.org/0000-0002-9311-102X","affiliations":[{"raw_affiliation_string":"Bytedance Inc., Seattle, USA","institution_ids":["https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014838990","display_name":"Lei Chen","orcid":"https://orcid.org/0009-0008-7975-0651"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Chen","raw_affiliation_strings":["Bytedance Inc., San Jose, USA"],"raw_orcid":"https://orcid.org/0009-0008-7975-0651","affiliations":[{"raw_affiliation_string":"Bytedance Inc., San Jose, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087120799","display_name":"Zhenzhe Zheng","orcid":"https://orcid.org/0000-0002-5094-5331"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenzhe Zheng","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5094-5331","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059190563","display_name":"Fan Wu","orcid":"https://orcid.org/0000-0003-0965-9058"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Wu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0965-9058","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100428808","display_name":"Guihai Chen","orcid":"https://orcid.org/0000-0002-6934-1685"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guihai Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6934-1685","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78636437,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2492","last_page":"2501"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998999834060669,"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":0.9998999834060669,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9901999831199646,"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":0.9789999723434448,"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/computer-science","display_name":"Computer science","score":0.8185762166976929},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.6528202295303345},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5864412188529968},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.5422192215919495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5406349301338196},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.4650007486343384},{"id":"https://openalex.org/keywords/privacy-protection","display_name":"Privacy protection","score":0.41833555698394775},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.36133551597595215},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3352758288383484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185762166976929},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.6528202295303345},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5864412188529968},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.5422192215919495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5406349301338196},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.4650007486343384},{"id":"https://openalex.org/C3017597292","wikidata":"https://www.wikidata.org/wiki/Q25052250","display_name":"Privacy protection","level":2,"score":0.41833555698394775},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.36133551597595215},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3352758288383484},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583780.3615019","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583780.3615019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2013823004","https://openalex.org/W2123820077","https://openalex.org/W2130099852","https://openalex.org/W2626769593","https://openalex.org/W2913668833","https://openalex.org/W2966684267","https://openalex.org/W2989060401","https://openalex.org/W3103107468","https://openalex.org/W3129519326","https://openalex.org/W3198751165","https://openalex.org/W3211848727","https://openalex.org/W4200406332","https://openalex.org/W4213044365","https://openalex.org/W4290997080","https://openalex.org/W4295036142","https://openalex.org/W4296982580","https://openalex.org/W4297685029","https://openalex.org/W4306952702","https://openalex.org/W4307823734","https://openalex.org/W6600234944","https://openalex.org/W6824583106","https://openalex.org/W6825026517"],"related_works":["https://openalex.org/W3022534164","https://openalex.org/W4396832952","https://openalex.org/W2138522421","https://openalex.org/W3046095319","https://openalex.org/W3197497514","https://openalex.org/W1591172238","https://openalex.org/W2111194702","https://openalex.org/W2972172135","https://openalex.org/W2116878667","https://openalex.org/W315296216"],"abstract_inverted_index":{"With":[0],"increasing":[1],"concern":[2],"over":[3,207],"data":[4,45,60],"privacy,":[5,61,64],"split":[6,69],"learning":[7,15],"has":[8],"become":[9],"a":[10,40,98,147,176],"widely":[11],"used":[12],"distributed":[13],"machine":[14],"paradigm":[16],"in":[17,68,214],"practice,":[18],"where":[19],"two":[20,50],"participants":[21],"(namely":[22],"the":[23,27,49,81,85,107,112,119,158,171,184,197],"non-label":[24,120],"party":[25,109,160,173],"and":[26,33,37,71,129,170,180,218],"label":[28,63,78,108,159,172,216],"party)":[29],"own":[30],"raw":[31,34,44,127],"features":[32],"labels":[35,117,139,198],"respectively,":[36],"jointly":[38],"train":[39],"model.":[41],"Although":[42],"no":[43],"is":[46,65,91,166],"communicated":[47],"between":[48,178],"parties":[51],"during":[52],"model":[53],"training,":[54],"several":[55,74],"works":[56],"have":[57,72,204],"demonstrated":[58],"that":[59],"especially":[62],"still":[66],"vulnerable":[67],"learning,":[70],"proposed":[73],"defense":[75],"algorithms":[76,90],"against":[77,199],"attacks.":[79,202],"However,":[80],"theoretical":[82],"guarantee":[83],"on":[84,126,154],"privacy":[86,124,179,217],"preservation":[87,125],"of":[88],"these":[89],"limited.":[92],"In":[93,105,187],"this":[94],"work,":[95],"we":[96,131,189],"propose":[97],"novel":[99],"Private":[100],"Split":[101],"Learning":[102],"Framework":[103],"(PSLF).":[104],"PSLF,":[106],"shares":[110],"only":[111],"gradients":[113],"computed":[114],"by":[115,182],"flipped":[116,163],"with":[118],"party,":[121],"which":[122],"improves":[123],"labels,":[128],"meanwhile,":[130],"further":[132,195],"design":[133,146,190],"an":[134,191],"extra":[135],"sub-model":[136],"from":[137],"true":[138],"to":[140,161,194,210],"improve":[141],"prediction":[142,221],"accuracy.":[143,222],"We":[144,203],"also":[145],"Flipped":[148],"Multi-Label":[149],"Generation":[150],"mechanism":[151],"(FMLG)":[152],"based":[153],"randomized":[155],"response":[156],"for":[157],"generate":[162],"labels.":[164],"FMLG":[165],"proven":[167],"differentially":[168],"private":[169],"could":[174],"make":[175],"trade-off":[177],"utility":[181],"setting":[183],"DP":[185],"budget.":[186],"addition,":[188],"upsampling":[192],"method":[193],"protect":[196],"some":[200],"existing":[201],"evaluated":[205],"PSLF":[206],"real-world":[208],"datasets":[209],"demonstrate":[211],"its":[212],"effectiveness":[213],"protecting":[215],"achieving":[219],"promising":[220]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}