{"id":"https://openalex.org/W4402159880","doi":"https://doi.org/10.1109/icc51166.2024.10623019","title":"Breakwater: Securing Federated Learning from Malicious Model Poisoning via Self-Debiasing","display_name":"Breakwater: Securing Federated Learning from Malicious Model Poisoning via Self-Debiasing","publication_year":2024,"publication_date":"2024-06-09","ids":{"openalex":"https://openalex.org/W4402159880","doi":"https://doi.org/10.1109/icc51166.2024.10623019"},"language":"en","primary_location":{"id":"doi:10.1109/icc51166.2024.10623019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc51166.2024.10623019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2024 - IEEE International Conference on Communications","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/A5106954549","display_name":"Yeawon You","orcid":null},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeawon You","raw_affiliation_strings":["Ewha Womans University,Department of Computer Science and Engineering,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ewha Womans University,Department of Computer Science and Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085520447","display_name":"JinYi Yoon","orcid":"https://orcid.org/0000-0001-9457-4432"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"JinYi Yoon","raw_affiliation_strings":["Virginia Tech,Department of Computer Science,Blacksburg,VA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech,Department of Computer Science,Blacksburg,VA,USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006920003","display_name":"HyungJune Lee","orcid":"https://orcid.org/0000-0003-4655-4298"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"HyungJune Lee","raw_affiliation_strings":["Ewha Womans University,Department of Computer Science and Engineering,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ewha Womans University,Department of Computer Science and Engineering,Seoul,South Korea","institution_ids":["https://openalex.org/I138925566"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3556,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53904239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3956","last_page":"3961"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9983000159263611,"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":0.9983000159263611,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11424","display_name":"Security and Verification in Computing","score":0.9975000023841858,"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/debiasing","display_name":"Debiasing","score":0.9710642695426941},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.715965986251831},{"id":"https://openalex.org/keywords/breakwater","display_name":"Breakwater","score":0.5933950543403625},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.5467112064361572},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1010591983795166}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.9710642695426941},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715965986251831},{"id":"https://openalex.org/C25282124","wikidata":"https://www.wikidata.org/wiki/Q215635","display_name":"Breakwater","level":2,"score":0.5933950543403625},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5467112064361572},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1010591983795166},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.0},{"id":"https://openalex.org/C187320778","wikidata":"https://www.wikidata.org/wiki/Q1349130","display_name":"Geotechnical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc51166.2024.10623019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc51166.2024.10623019","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2024 - IEEE International Conference on Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1983249544","https://openalex.org/W2112796928","https://openalex.org/W2139587243","https://openalex.org/W2410099853","https://openalex.org/W2750384547","https://openalex.org/W2752689052","https://openalex.org/W2788308444","https://openalex.org/W2982083293","https://openalex.org/W3047140762","https://openalex.org/W4226116859","https://openalex.org/W4288578176","https://openalex.org/W6728757088","https://openalex.org/W6743688258","https://openalex.org/W6743821447","https://openalex.org/W6748268456","https://openalex.org/W6748786018","https://openalex.org/W6754358263","https://openalex.org/W6758201434"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4362554880","https://openalex.org/W4281684980","https://openalex.org/W4386875279","https://openalex.org/W2171721708","https://openalex.org/W4390963114","https://openalex.org/W3214527415","https://openalex.org/W4287887864","https://openalex.org/W1495104519"],"abstract_inverted_index":{"Deep":[0],"learning":[1,27,92,160,188,209],"models":[2,40],"deployed":[3],"on":[4,111,158],"edge":[5,36,73,186],"devices":[6],"leverage":[7],"locally":[8,41],"collected":[9],"data":[10,20,49],"to":[11,38,124,154,194],"extract":[12],"intelligence,":[13],"mitigating":[14],"privacy":[15],"concerns":[16],"associated":[17],"with":[18,103,190],"external":[19],"sharing.":[21],"Edge":[22],"federated":[23,74,91,159,187],"learning,":[24],"an":[25],"on-device":[26,78],"paradigm,":[28],"has":[29],"emerged":[30],"as":[31],"a":[32,66,117,163,202],"promising":[33],"solution,":[34],"allowing":[35],"nodes":[37,102],"train":[39],"and":[42,60,87,139,206],"share":[43],"only":[44],"the":[45,90,98,112,128,145,148,155,181,184],"trained":[46],"weights,":[47,143],"preserving":[48],"privacy.":[50],"However,":[51],"it":[52],"also":[53],"poses":[54],"critical":[55],"challenges":[56],"of":[57,89,100,147,183,192],"network":[58],"burden":[59],"potential":[61,107],"model":[62,172],"poisoning.":[63],"We":[64,76,175],"introduce":[65],"self-debiasing":[67,118],"security":[68,86],"framework":[69,95,137],"Breakwater":[70,136],"for":[71],"multi-hop":[72,185],"learning.":[75],"incorporate":[77],"malicious":[79,108],"weight":[80,129],"discriminator":[81],"at":[82],"each":[83],"participant,":[84],"enhancing":[85,180],"robustness":[88],"process.":[93],"The":[94],"strategically":[96],"balances":[97],"benefits":[99],"participating":[101],"timely":[104],"defenses":[105],"against":[106,171],"clients.":[109],"Based":[110],"discriminator,":[113],"we":[114],"further":[115],"embed":[116],"mechanism":[119],"that":[120,165],"can":[121],"determine":[122],"whether":[123],"retain":[125],"or":[126],"discard":[127],"propagation":[130],"from":[131],"its":[132,177],"child":[133],"nodes.":[134],"Our":[135,151],"identifies":[138],"filters":[140],"out":[141],"harmful":[142],"ensuring":[144],"integrity":[146],"global":[149],"model.":[150],"work":[152],"contributes":[153],"ongoing":[156],"discourse":[157],"security,":[161],"presenting":[162],"solution":[164],"maintains":[166],"efficiency":[167],"while":[168],"robustly":[169],"defending":[170],"poisoning":[173],"threats.":[174],"demonstrate":[176],"efficacy":[178],"in":[179,197],"reliability":[182],"process":[189],"recovery":[191],"up":[193],"69":[195],"%":[196],"accuracy":[198],"under":[199],"attack,":[200],"offering":[201],"path":[203],"toward":[204],"secure":[205],"cooperative":[207],"distributed":[208],"environments.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}