{"id":"https://openalex.org/W7118955112","doi":"https://doi.org/10.1109/vtc2025-fall65116.2025.11310677","title":"Dual-VAE with Truncated Gaussian: An Unsupervised Defense Against Model Poisoning in Federated Learning","display_name":"Dual-VAE with Truncated Gaussian: An Unsupervised Defense Against Model Poisoning in Federated Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7118955112","doi":"https://doi.org/10.1109/vtc2025-fall65116.2025.11310677"},"language":null,"primary_location":{"id":"doi:10.1109/vtc2025-fall65116.2025.11310677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vtc2025-fall65116.2025.11310677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 102nd Vehicular Technology Conference (VTC2025-Fall)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5083549838","display_name":"Haoqi Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Haoqi Huang","raw_affiliation_strings":["Lassonde School of Engineering York University,Toronto,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lassonde School of Engineering York University,Toronto,Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122196235","display_name":"Ping Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ping Wang","raw_affiliation_strings":["Lassonde School of Engineering York University,Toronto,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lassonde School of Engineering York University,Toronto,Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122129974","display_name":"Om Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Om Kumar","raw_affiliation_strings":["Computer Science and Engineering Indian Institute of Technology Jodhpur,Jodhpur,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Indian Institute of Technology Jodhpur,Jodhpur,India","institution_ids":["https://openalex.org/I154549908"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5558000206947327,"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":0.5558000206947327,"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":0.30889999866485596,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.023800000548362732,"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/autoencoder","display_name":"Autoencoder","score":0.8205000162124634},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7117999792098999},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6086999773979187},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.5907999873161316},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5827999711036682},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4916999936103821},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44359999895095825},{"id":"https://openalex.org/keywords/gaussian-network-model","display_name":"Gaussian network model","score":0.43939998745918274},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4359999895095825}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8205000162124634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401000261306763},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7117999792098999},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6086999773979187},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5907999873161316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5842999815940857},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5827999711036682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5012999773025513},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4916999936103821},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44830000400543213},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44359999895095825},{"id":"https://openalex.org/C166550679","wikidata":"https://www.wikidata.org/wiki/Q263400","display_name":"Gaussian network model","level":3,"score":0.43939998745918274},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4359999895095825},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vtc2025-fall65116.2025.11310677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vtc2025-fall65116.2025.11310677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 102nd Vehicular Technology Conference (VTC2025-Fall)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.728599488735199}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2614254310","https://openalex.org/W2934302500","https://openalex.org/W3021654819","https://openalex.org/W3036791758","https://openalex.org/W3108027302","https://openalex.org/W3155912831","https://openalex.org/W3160147580","https://openalex.org/W3163105316","https://openalex.org/W3170790803","https://openalex.org/W3206807859","https://openalex.org/W3213330817","https://openalex.org/W4281639882","https://openalex.org/W4288057793","https://openalex.org/W4385210255"],"related_works":[],"abstract_inverted_index":{"Federated":[0],"learning":[1],"(FL)":[2],"enables":[3],"decentralized":[4],"model":[5,15,27,115],"training":[6],"while":[7],"preserving":[8],"data":[9],"privacy,":[10],"but":[11],"remains":[12],"vulnerable":[13],"to":[14,24,61,76],"poisoning":[16],"attacks,":[17],"where":[18],"malicious":[19],"clients":[20],"inject":[21],"harmful":[22],"updates":[23,53],"degrade":[25],"global":[26,114],"performance.":[28,116],"In":[29],"this":[30],"work,":[31],"we":[32],"propose":[33],"Dual-Variational":[34],"Autoencoder":[35],"with":[36,66,92],"truncated":[37,68],"Gaussian":[38,69,96],"(DVTG),":[39],"an":[40],"unsupervised":[41],"defense":[42],"framework":[43],"for":[44],"anomaly":[45,111],"detection.":[46],"The":[47],"first":[48],"VAE":[49,65],"filters":[50],"out":[51],"low-reconstruction-error":[52],"from":[54],"potentially":[55],"poisoned":[56],"data.":[57],"These":[58],"are":[59],"used":[60],"train":[62],"a":[63,67],"second":[64],"prior.":[70],"This":[71],"prior":[72],"constrains":[73],"latent":[74],"representations":[75],"high-density":[77],"regions":[78],"of":[79],"normal":[80],"behavior,":[81],"improving":[82],"robustness":[83],"against":[84],"noise":[85,97],"and":[86,94,106,113],"adversarial":[87],"manipulation.":[88],"Experiments":[89],"on":[90],"MNIST":[91],"sign-flipping":[93],"additive":[95],"attacks":[98],"show":[99],"that":[100],"our":[101],"method":[102],"outperforms":[103],"both":[104],"single-VAE":[105],"robust":[107],"aggregation":[108],"baselines":[109],"in":[110],"detection":[112]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-08T00:00:00"}