{"id":"https://openalex.org/W4407131029","doi":"https://doi.org/10.1109/imcom64595.2025.10857574","title":"Towards Robust Federated Learning: Investigating Poisoning Attacks Under Clients Data Heterogeneity","display_name":"Towards Robust Federated Learning: Investigating Poisoning Attacks Under Clients Data Heterogeneity","publication_year":2025,"publication_date":"2025-01-03","ids":{"openalex":"https://openalex.org/W4407131029","doi":"https://doi.org/10.1109/imcom64595.2025.10857574"},"language":"en","primary_location":{"id":"doi:10.1109/imcom64595.2025.10857574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/imcom64595.2025.10857574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 19th International Conference on Ubiquitous Information Management and Communication (IMCOM)","raw_type":"proceedings-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/A5116145098","display_name":"Abdenour Soubih","orcid":null},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Abdenour Soubih","raw_affiliation_strings":["College of Computing and Informatics, Sungkyunkwan University,Suwon,Korea"],"affiliations":[{"raw_affiliation_string":"College of Computing and Informatics, Sungkyunkwan University,Suwon,Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116145099","display_name":"Seyyid Ahmed Lahmer","orcid":null},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Seyyid Ahmed Lahmer","raw_affiliation_strings":["University of Padova,Department of Information Engineering,Padua,Italy"],"affiliations":[{"raw_affiliation_string":"University of Padova,Department of Information Engineering,Padua,Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042456819","display_name":"Mohammed Abuhamad","orcid":"https://orcid.org/0000-0002-3368-6024"},"institutions":[{"id":"https://openalex.org/I1925986","display_name":"Loyola University Chicago","ror":"https://ror.org/04b6x2g63","country_code":"US","type":"education","lineage":["https://openalex.org/I1925986"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammed Abuhamad","raw_affiliation_strings":["Loyola University Chicago,Department of Computer Science,Chicago,USA"],"affiliations":[{"raw_affiliation_string":"Loyola University Chicago,Department of Computer Science,Chicago,USA","institution_ids":["https://openalex.org/I1925986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023828527","display_name":"Tamer Abuhmed","orcid":"https://orcid.org/0000-0001-9232-4843"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tamer Abuhmed","raw_affiliation_strings":["College of Computing and Informatics, Sungkyunkwan University,Suwon,Korea"],"affiliations":[{"raw_affiliation_string":"College of Computing and Informatics, Sungkyunkwan University,Suwon,Korea","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5116145098"],"corresponding_institution_ids":["https://openalex.org/I848706"],"apc_list":null,"apc_paid":null,"fwci":2.6579,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88724988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9707000255584717,"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":0.9707000255584717,"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":0.7705844640731812},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.5901514291763306},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.40440845489501953},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32896992564201355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27834761142730713}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7705844640731812},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5901514291763306},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.40440845489501953},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32896992564201355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27834761142730713}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/imcom64595.2025.10857574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/imcom64595.2025.10857574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 19th International Conference on Ubiquitous Information Management and Communication (IMCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[{"id":"https://openalex.org/G1128486320","display_name":null,"funder_award_id":"2021R1A2C1011198","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2014352947","https://openalex.org/W3204423820","https://openalex.org/W4285279512","https://openalex.org/W4317436377","https://openalex.org/W4396844106","https://openalex.org/W4401751761","https://openalex.org/W6676935882","https://openalex.org/W6684072790","https://openalex.org/W6728757088","https://openalex.org/W6759238902","https://openalex.org/W6763048141","https://openalex.org/W6767676916","https://openalex.org/W6781318954","https://openalex.org/W6853626954","https://openalex.org/W6855977931","https://openalex.org/W6863977488","https://openalex.org/W6864820886","https://openalex.org/W7014198846"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4298221930","https://openalex.org/W2390279801","https://openalex.org/W2777914285","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4378677776","https://openalex.org/W3176937389"],"abstract_inverted_index":{"Federated":[0],"Learning":[1],"(FL)":[2],"offers":[3],"a":[4,13,112],"privacy-preserving":[5],"solution":[6],"by":[7,126,140],"enabling":[8],"multiple":[9],"clients":[10,110],"to":[11,101,153],"train":[12],"shared":[14,125],"model":[15,155],"collaboratively":[16],"without":[17],"centralizing":[18],"data.":[19],"However,":[20],"the":[21,39,50,62,65,69,91,106,120,146],"decentralized":[22],"nature":[23],"of":[24,41,52,64,71,93,108,122,135,148],"FL":[25],"presents":[26],"challenges,":[27],"particularly":[28],"regarding":[29],"security":[30],"and":[31,57,76],"performance":[32,118,156],"under":[33,44,157],"adversarial":[34,158],"conditions.":[35,159],"This":[36],"paper":[37],"investigates":[38],"effects":[40,70,92],"poisoning":[42,72,123,136],"attacks":[43,73],"data":[45,88],"heterogeneity.":[46],"Our":[47,83],"experiments":[48],"evaluate":[49],"impact":[51],"varying":[53],"malicious":[54,109,128],"client":[55],"fractions":[56],"poison":[58],"concentration":[59],"levels":[60,134],"on":[61,74],"accuracy":[63],"model.":[66],"We":[67,103],"explore":[68],"FedAvg":[75],"FedNova":[77,96],"models":[78],"using":[79],"medical":[80],"imaging":[81],"tasks.":[82],"findings":[84],"reveal":[85],"that":[86,105,131],"increasing":[87],"heterogeneity":[89],"exacerbates":[90],"poisoning,":[94],"with":[95],"demonstrating":[97],"greater":[98],"resilience":[99],"compared":[100],"FedAvg.":[102],"found":[104],"number":[107],"plays":[111],"more":[113],"significant":[114],"role":[115],"in":[116],"degrading":[117],"than":[119],"ratio":[121],"samples":[124],"each":[127],"client,":[129],"suggesting":[130],"even":[132],"modest":[133],"can":[137],"be":[138],"tolerated":[139],"most":[141],"algorithms.":[142],"The":[143],"study":[144],"highlights":[145],"importance":[147],"developing":[149],"robust":[150],"defense":[151],"mechanisms":[152],"maintain":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}