{"id":"https://openalex.org/W4391093146","doi":"https://doi.org/10.1109/tifs.2024.3356821","title":"Similarity-Based Label Inference Attack Against Training and Inference of Split Learning","display_name":"Similarity-Based Label Inference Attack Against Training and Inference of Split Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391093146","doi":"https://doi.org/10.1109/tifs.2024.3356821"},"language":"en","primary_location":{"id":"doi:10.1109/tifs.2024.3356821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2024.3356821","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-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/A5070375205","display_name":"Junlin Liu","orcid":"https://orcid.org/0000-0002-4981-1010"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlin Liu","raw_affiliation_strings":["National Engineering Research Center for Mobile Network Technologies, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4981-1010","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Mobile Network Technologies, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090327058","display_name":"Xinchen Lyu","orcid":"https://orcid.org/0000-0003-0404-4310"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinchen Lyu","raw_affiliation_strings":["National Engineering Research Center for Mobile Network Technologies, Beijing University of Posts and Telecommunications, Beijing, China","Department of Broadband Communication, Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0404-4310","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Mobile Network Technologies, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Department of Broadband Communication, Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018587643","display_name":"Qimei Cui","orcid":"https://orcid.org/0000-0003-1720-220X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qimei Cui","raw_affiliation_strings":["National Engineering Research Center for Mobile Network Technologies, Beijing University of Posts and Telecommunications, Beijing, China","Department of Broadband Communication, Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1720-220X","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Mobile Network Technologies, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Department of Broadband Communication, Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624765","display_name":"Xiaofeng Tao","orcid":"https://orcid.org/0000-0001-9518-1622"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Tao","raw_affiliation_strings":["National Engineering Research Center for Mobile Network Technologies, Beijing University of Posts and Telecommunications, Beijing, China","Department of Broadband Communication, Pengcheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9518-1622","affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Mobile Network Technologies, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Department of Broadband Communication, Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.0858,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.96678809,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"19","issue":null,"first_page":"2881","last_page":"2895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9660999774932861,"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":0.9660999774932861,"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":0.8154257535934448},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.8039071559906006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6808058619499207},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6397637128829956},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5904287099838257},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45357951521873474},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4164086580276489}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8154257535934448},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8039071559906006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6808058619499207},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6397637128829956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5904287099838257},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45357951521873474},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4164086580276489},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tifs.2024.3356821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2024.3356821","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2094305956","display_name":null,"funder_award_id":"62371059","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8570612936","display_name":null,"funder_award_id":"PCL2021A15","funder_id":"https://openalex.org/F4320318558","funder_display_name":"Peng Cheng Laboratory"}],"funders":[{"id":"https://openalex.org/F4320318558","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W1849277567","https://openalex.org/W2027595342","https://openalex.org/W2117539524","https://openalex.org/W2160815625","https://openalex.org/W2194775991","https://openalex.org/W2222512263","https://openalex.org/W2473418344","https://openalex.org/W2535199873","https://openalex.org/W2535690855","https://openalex.org/W2541884796","https://openalex.org/W2591882872","https://openalex.org/W2616274621","https://openalex.org/W2618530766","https://openalex.org/W2750384547","https://openalex.org/W2774000609","https://openalex.org/W2782492233","https://openalex.org/W2782812883","https://openalex.org/W2783606427","https://openalex.org/W2785456003","https://openalex.org/W2912023992","https://openalex.org/W2963209930","https://openalex.org/W2963456518","https://openalex.org/W2964162474","https://openalex.org/W2970408908","https://openalex.org/W2989060401","https://openalex.org/W2998600867","https://openalex.org/W3000479830","https://openalex.org/W3000983008","https://openalex.org/W3009048827","https://openalex.org/W3009196798","https://openalex.org/W3012125688","https://openalex.org/W3018102029","https://openalex.org/W3045086295","https://openalex.org/W3048168663","https://openalex.org/W3091068973","https://openalex.org/W3091884625","https://openalex.org/W3103107468","https://openalex.org/W3105915864","https://openalex.org/W3107794213","https://openalex.org/W3109503640","https://openalex.org/W3118608800","https://openalex.org/W3126166521","https://openalex.org/W3142852780","https://openalex.org/W3198751165","https://openalex.org/W3199638890","https://openalex.org/W3209673140","https://openalex.org/W3213008925","https://openalex.org/W4226523637","https://openalex.org/W4229083957","https://openalex.org/W4286961857","https://openalex.org/W4287605110","https://openalex.org/W4289147263","https://openalex.org/W4296411155","https://openalex.org/W4297779784","https://openalex.org/W4316661188","https://openalex.org/W4317549124","https://openalex.org/W4318619660","https://openalex.org/W4367369823","https://openalex.org/W4372266209","https://openalex.org/W6728757088","https://openalex.org/W6743688258","https://openalex.org/W6746839373","https://openalex.org/W6748579526","https://openalex.org/W6756436328","https://openalex.org/W6764838729","https://openalex.org/W6766978945","https://openalex.org/W6768234139","https://openalex.org/W6772284903","https://openalex.org/W6773039429","https://openalex.org/W6782083561","https://openalex.org/W6786343911","https://openalex.org/W6787972765","https://openalex.org/W6790338629","https://openalex.org/W6791120749","https://openalex.org/W6792742759","https://openalex.org/W6801929890","https://openalex.org/W6803491735","https://openalex.org/W6811348264","https://openalex.org/W6848881621"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W2375480909","https://openalex.org/W2353314428","https://openalex.org/W4321636575","https://openalex.org/W2357796999","https://openalex.org/W2045526782","https://openalex.org/W2012019886","https://openalex.org/W2741131631","https://openalex.org/W1986418932","https://openalex.org/W2166090428"],"abstract_inverted_index":{"Split":[0],"learning":[1,11,42],"is":[2,43],"a":[3],"promising":[4],"paradigm":[5],"for":[6,45,98],"privacy-preserving":[7],"distributed":[8],"learning.":[9],"The":[10,157],"model":[12],"can":[13,77,148,160],"be":[14,20,112],"cut":[15,34],"into":[16],"multiple":[17],"portions":[18],"to":[19,111,128,151],"collaboratively":[21],"trained":[22],"at":[23,32],"the":[24,29,33,37,53,58,65,80,86,92,105,119,131,136,145],"participants":[25],"by":[26],"exchanging":[27],"only":[28],"intermediate":[30,55],"results":[31,142],"layer.":[35],"Understanding":[36],"security":[38],"performance":[39],"of":[40,74,154],"split":[41,75],"critical":[44],"many":[46],"privacy-sensitive":[47],"applications.":[48],"This":[49],"paper":[50],"shows":[51],"that":[52,144],"exchanged":[54],"results,":[56],"including":[57,170],"smashed":[59,101],"data":[60],"(i.e.,":[61],"extracted":[62],"features":[63],"from":[64],"raw":[66],"data)":[67],"and":[68,72,90,94,100,138,177],"gradients":[69,99],"during":[70,134],"training":[71,137],"inference":[73,126,139],"learning,":[76],"already":[78],"reveal":[79],"private":[81,132],"labels.":[82],"We":[83],"mathematically":[84],"analyze":[85],"potential":[87],"label":[88,125,155,172],"leakages":[89],"propose":[91],"cosine":[93],"Euclidean":[95,115],"similarity":[96,107,120],"measurements":[97,108],"data,":[102],"respectively.":[103],"Then,":[104],"two":[106],"are":[109],"shown":[110],"unified":[113],"in":[114],"space.":[116],"Based":[117],"on":[118],"metric,":[121],"we":[122],"design":[123],"three":[124],"attacks":[127],"efficiently":[129],"recover":[130],"labels":[133],"both":[135],"phases.":[140],"Experimental":[141],"validate":[143],"proposed":[146,158],"approaches":[147],"achieve":[149,162],"close":[150],"100%":[152],"accuracy":[153],"attacks.":[156],"attack":[159],"still":[161],"accurate":[163],"predictions":[164],"against":[165],"various":[166],"state-of-the-art":[167],"defense":[168],"mechanisms,":[169],"DP-SGD,":[171],"differential":[173],"privacy,":[174],"gradient":[175],"compression,":[176],"Marvell.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2024-01-23T00:00:00"}