{"id":"https://openalex.org/W4402980115","doi":"https://doi.org/10.1109/icme57554.2024.10687918","title":"FedCL: Detecting Backdoor Attacks in Federated Learning with Confidence Levels","display_name":"FedCL: Detecting Backdoor Attacks in Federated Learning with Confidence Levels","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980115","doi":"https://doi.org/10.1109/icme57554.2024.10687918"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5114236932","display_name":"Jinhe Long","orcid":null},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinhe Long","raw_affiliation_strings":["Fuzhou University,College of Computer and Data Science,Fuzhou,China"],"affiliations":[{"raw_affiliation_string":"Fuzhou University,College of Computer and Data Science,Fuzhou,China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101430107","display_name":"Zekai Chen","orcid":"https://orcid.org/0000-0002-5564-137X"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zekai Chen","raw_affiliation_strings":["Fuzhou University,College of Computer and Data Science,Fuzhou,China"],"affiliations":[{"raw_affiliation_string":"Fuzhou University,College of Computer and Data Science,Fuzhou,China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102793940","display_name":"Fuyi Wang","orcid":"https://orcid.org/0000-0002-8216-3238"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Fuyi Wang","raw_affiliation_strings":["Deakin University,School of Information Technology,Waurn Ponds"],"affiliations":[{"raw_affiliation_string":"Deakin University,School of Information Technology,Waurn Ponds","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001657111","display_name":"Jianping Cai","orcid":"https://orcid.org/0000-0003-1575-8239"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianping Cai","raw_affiliation_strings":["Fuzhou University,College of Computer and Data Science,Fuzhou,China"],"affiliations":[{"raw_affiliation_string":"Fuzhou University,College of Computer and Data Science,Fuzhou,China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058120371","display_name":"Ximeng Liu","orcid":"https://orcid.org/0000-0002-4238-3295"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ximeng Liu","raw_affiliation_strings":["Fuzhou University,College of Computer and Data Science,Fuzhou,China"],"affiliations":[{"raw_affiliation_string":"Fuzhou University,College of Computer and Data Science,Fuzhou,China","institution_ids":["https://openalex.org/I80947539"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5114236932"],"corresponding_institution_ids":["https://openalex.org/I80947539"],"apc_list":null,"apc_paid":null,"fwci":1.0911,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.81631412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9876000285148621,"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":0.9876000285148621,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9793999791145325,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.972599983215332,"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":0.9903673529624939},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7118188142776489},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.4782673120498657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38429006934165955}],"concepts":[{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.9903673529624939},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7118188142776489},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4782673120498657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38429006934165955}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10687918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W3099060745","https://openalex.org/W3138597937","https://openalex.org/W3175919946","https://openalex.org/W3204548896","https://openalex.org/W4213446860","https://openalex.org/W4221129260","https://openalex.org/W4281398987","https://openalex.org/W4386106329","https://openalex.org/W4386160485"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4320031223","https://openalex.org/W4200629851","https://openalex.org/W4281902577","https://openalex.org/W4309417370","https://openalex.org/W4292107232","https://openalex.org/W3009072493","https://openalex.org/W4386080799","https://openalex.org/W4401407399"],"abstract_inverted_index":{"Federated":[0],"Learning":[1],"(FL)":[2],"enables":[3],"multiple":[4],"clients":[5],"to":[6,25,29,42,110],"collaborate":[7],"in":[8,143],"training":[9],"neural":[10],"network":[11],"models":[12,97],"while":[13],"retaining":[14],"their":[15],"private":[16],"data":[17],"locally.":[18],"Despite":[19],"its":[20,30],"advantages,":[21],"FL":[22],"is":[23],"vulnerable":[24],"backdoor":[26,79,90,96,117],"attacks":[27,118],"due":[28],"distributed":[31],"nature.":[32],"Attackers":[33],"introduce":[34,87],"triggers":[35],"into":[36],"the":[37,76,100,121,137,144],"global":[38,122],"model,":[39],"causing":[40],"it":[41,106],"make":[43],"specified":[44],"predictions":[45],"on":[46,58,67],"inputs":[47],"containing":[48],"these":[49],"triggers.":[50],"Existing":[51],"detection":[52],"or":[53],"clustering":[54],"defense":[55,91,140],"methods":[56],"based":[57,66],"distance":[59],"and":[60,69],"similarity":[61],"have":[62],"significant":[63],"limitations.":[64],"Methods":[65],"clipping":[68,109],"adding":[70],"noise":[71],"can":[72],"only":[73],"slightly":[74],"mitigate":[75],"impact":[77],"of":[78,102],"attacks.":[80],"To":[81],"achieve":[82],"a":[83,89],"better":[84],"defense,":[85],"we":[86],"FedCL,":[88],"framework":[92],"that":[93,128],"accurately":[94],"detects":[95],"by":[98,132],"assessing":[99],"uncertainty":[101],"model":[103,112],"predictions.":[104],"Additionally,":[105],"employs":[107],"dynamic":[108],"limit":[111],"updates\u2019":[113],"impact,":[114],"successfully":[115],"mitigating":[116],"without":[119],"compromising":[120],"model\u2019s":[123],"accuracy.":[124],"The":[125],"experiments":[126],"indicate":[127],"FedCL":[129],"moderately":[130],"improves":[131],"0.01%\u2191":[133],"\u223c":[134],"85.78%\u2191":[135],"than":[136],"state-of-the-art":[138],"(SOTA)":[139],"methods,":[141],"especially":[142],"CIFAR-10":[145],"task":[146],"trained":[147],"with":[148],"more":[149],"complex":[150],"networks.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}