{"id":"https://openalex.org/W7164001024","doi":"https://doi.org/10.48550/arxiv.2606.08027","title":"CausShield: Sample Reconstruction-Resilient Vertical FL via Causal Representation Learning","display_name":"CausShield: Sample Reconstruction-Resilient Vertical FL via Causal Representation Learning","publication_year":2026,"publication_date":"2026-06-06","ids":{"openalex":"https://openalex.org/W7164001024","doi":"https://doi.org/10.48550/arxiv.2606.08027"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.08027","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08027","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":null,"license_id":null,"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.2606.08027","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138267912","display_name":"Yongqi Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Yongqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138267454","display_name":"Yansong Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Yansong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138215029","display_name":"Siguang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Siguang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138217602","display_name":"Anmin Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Anmin","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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.8427000045776367,"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":0.8427000045776367,"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":0.0851999968290329,"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":0.02239999920129776,"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/robustness","display_name":"Robustness (evolution)","score":0.6739000082015991},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5855000019073486},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5569999814033508},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5339000225067139},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5315999984741211},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.531000018119812},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.4449999928474426},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.4438000023365021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741599977016449},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6739000082015991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6047999858856201},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5569999814033508},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5315999984741211},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.531000018119812},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5026000142097473},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3391999900341034},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3294000029563904},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2743000090122223},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.08027","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08027","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.08027","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08027","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4925938844680786}],"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],"federated":[1],"learning":[2,7,106],"(VFL)":[3],"is":[4,160,186],"a":[5,35,77,87,93,125,180],"distributed":[6],"paradigm":[8],"that":[9,98,196,229],"leverages":[10],"vertically":[11],"partitioned":[12],"features":[13,52,91,110],"across":[14],"isolated":[15],"parties":[16],"without":[17],"sharing":[18],"raw":[19,94],"samples;":[20],"however,":[21],"it":[22],"remains":[23],"vulnerable":[24],"to":[25,33,45,59,68,104,128,152,164],"active":[26],"sample":[27,95],"reconstruction":[28,221],"attacks.":[29],"Existing":[30],"defenses":[31],"fail":[32],"achieve":[34],"satisfactory":[36],"trade-off":[37],"between":[38,138],"model":[39,67,80,170,236],"utility":[40,171],"and":[41,83,102,141,149,216,238],"privacy":[42,155,174,234],"protection,":[43,235],"due":[44,163],"either":[46],"suppressing":[47],"task-relevant":[48,148],"information":[49],"alongside":[50],"privacy-sensitive":[51],"or":[53],"relying":[54],"on":[55],"end-to-end":[56],"supervised":[57],"training":[58],"converge":[60],"the":[61,66,105,135,139,142,158,165,199],"defense":[62],"module,":[63],"which":[64,185],"exposes":[65],"early-epoch":[69],"vulnerability.":[70],"To":[71],"address":[72,177],"this":[73,130,178],"challenge,":[74],"we":[75,123],"adopt":[76],"structural":[78],"causal":[79,90],"(SCM)":[81],"insight":[82],"construct":[84],"CausShield.":[85],"From":[86],"task-learning":[88],"standpoint,":[89],"within":[92],"are":[96,99,111],"those":[97],"directly":[100],"relevant":[101],"contributory":[103],"objective,":[107],"whereas":[108],"non-causal":[109],"task-irrelevant":[112,150],"but":[113],"often":[114],"encode":[115],"sample-specific":[116],"private":[117],"information,":[118],"thereby":[119],"facilitating":[120],"reconstruction.":[121],"Importantly,":[122],"lay":[124],"theoretical":[126],"foundation":[127],"prove":[129,195],"insight.":[131],"CausShield":[132,197,208,230],"thus":[133],"decomposes":[134],"shared":[136],"representations":[137],"client":[140],"coordinating":[143],"server":[144],"in":[145,233],"VFL":[146],"into":[147],"components":[151],"ensure":[153],"full-cycle":[154],"protection.":[156],"Nonetheless,":[157],"decomposition":[159],"inherently":[161],"challenging":[162],"dual":[166],"objectives":[167],"of":[168,202],"preserving":[169],"while":[172],"mitigating":[173],"leakage.":[175],"We":[176,192],"via":[179],"carefully":[181],"formulated":[182],"optimization":[183],"problem,":[184],"solved":[187],"through":[188],"unsupervised":[189],"representation":[190],"learning.":[191],"further":[193],"theoretically":[194],"preserves":[198],"convergence":[200],"behavior":[201],"standard":[203],"VFL.":[204],"Extensive":[205],"experiments":[206],"compare":[207],"against":[209,219],"seven":[210],"SOTAs,":[211],"including":[212],"InvL":[213],"(USENIX":[214],"Security'25),":[215],"evaluate":[217],"robustness":[218],"advanced":[220],"attacks":[222],"such":[223],"as":[224],"URVFL":[225],"(NDSS'25).":[226],"Results":[227],"demonstrate":[228],"consistently":[231],"outperforms":[232],"utility,":[237],"computational":[239],"efficiency.":[240]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-10T00:00:00"}