{"id":"https://openalex.org/W7151523637","doi":"https://doi.org/10.48550/arxiv.2604.03595","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","display_name":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","publication_year":2026,"publication_date":"2026-04-04","ids":{"openalex":"https://openalex.org/W7151523637","doi":"https://doi.org/10.48550/arxiv.2604.03595"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.03595","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03595","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.03595","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082388188","display_name":"Yuhan Shui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shui, Yuhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133134602","display_name":"Ruobin Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Ruobin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114414490","display_name":"Zhihao Dou","orcid":"https://orcid.org/0000-0002-3525-7442"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dou, Zhihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133092240","display_name":"Zhiqiang Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Zhiqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.6967999935150146,"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":0.6967999935150146,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.13809999823570251,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.032999999821186066,"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/backdoor","display_name":"Backdoor","score":0.9726999998092651},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7583000063896179},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6694999933242798},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4950000047683716},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4921000003814697},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.37070000171661377}],"concepts":[{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.9726999998092651},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7583000063896179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6825000047683716},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6694999933242798},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4950000047683716},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4921000003814697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4090000092983246},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3682999908924103},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36309999227523804},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.33709999918937683},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2628999948501587},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C98214594","wikidata":"https://www.wikidata.org/wiki/Q850275","display_name":"Conformal map","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.03595","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03595","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.03595","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03595","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6300370097160339}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vertical":[0],"split":[1,77],"learning":[2,78],"(SL)":[3],"enables":[4],"collaborative":[5],"model":[6,48],"training":[7],"across":[8],"parties":[9],"holding":[10],"complementary":[11],"features":[12],"without":[13],"sharing":[14],"raw":[15],"data,":[16],"but":[17],"recent":[18],"work":[19],"has":[20],"shown":[21],"that":[22,44,72,95,118,162],"it":[23],"is":[24,90],"highly":[25],"vulnerable":[26],"to":[27,52,138],"poisoning-based":[28],"backdoor":[29],"attacks":[30],"operating":[31],"on":[32,148],"intermediate":[33],"embeddings.":[34,143],"By":[35],"compromising":[36],"malicious":[37],"clients,":[38],"adversaries":[39],"can":[40],"inject":[41],"stealthy":[42],"triggers":[43],"manipulate":[45],"the":[46,74,85,93,99],"server-side":[47,70],"while":[49],"remaining":[50],"difficult":[51],"detect,":[53],"and":[54,123,140,153],"existing":[55],"defenses":[56],"provide":[57],"limited":[58],"robustness":[59,75],"against":[60],"adaptive":[61],"attacks.":[62],"In":[63],"this":[64,111],"paper,":[65],"we":[66],"propose":[67],"ProtoGuard-SL,":[68],"a":[69,115,127,132],"defense":[71],"improves":[73],"of":[76],"by":[79,92,131],"exploiting":[80],"class-conditional":[81],"representation":[82],"consistency":[83],"in":[84],"embedding":[86],"space.":[87],"Our":[88],"approach":[89],"motivated":[91],"observation":[94],"benign":[96],"embeddings":[97,108,125],"within":[98],"same":[100],"class":[101,121],"exhibit":[102],"stable":[103],"semantic":[104],"alignment,":[105],"whereas":[106],"poisoned":[107],"inevitably":[109],"disrupt":[110],"structure.":[112],"ProtoGuard-SL":[113],"adopts":[114],"two-stage":[116],"framework":[117],"constructs":[119],"robust":[120],"prototypes":[122],"transforms":[124],"into":[126],"prototype-consistency":[128],"representation,":[129],"followed":[130],"class-conditional,":[133],"distribution-free":[134],"conformal":[135],"filtering":[136],"strategy":[137],"identify":[139],"remove":[141],"anomalous":[142],"Extensive":[144],"experiments":[145],"are":[146],"conducted":[147],"three":[149,157],"datasets,":[150],"CIFAR-10,":[151],"SVHN,":[152],"Bank":[154],"Marketing,":[155],"under":[156],"different":[158],"attack":[159],"settings":[160],"demonstrate":[161],"our":[163],"method":[164],"achieves":[165],"state-of-the-art":[166],"performance.":[167]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-08T00:00:00"}