{"id":"https://openalex.org/W7124863268","doi":"https://doi.org/10.1109/tifs.2026.3655920","title":"Backdoor Detection in Federated Learning With Feature Map: A Multi-Task Learning Perspective","display_name":"Backdoor Detection in Federated Learning With Feature Map: A Multi-Task Learning Perspective","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7124863268","doi":"https://doi.org/10.1109/tifs.2026.3655920"},"language":null,"primary_location":{"id":"doi:10.1109/tifs.2026.3655920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2026.3655920","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-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/A5048347888","display_name":"Yifan Sui","orcid":"https://orcid.org/0009-0005-2261-5772"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifan Sui","raw_affiliation_strings":["Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123398608","display_name":"Yongqi Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqi Sun","raw_affiliation_strings":["Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110613499","display_name":"Naiyue Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Naiyue Chen","raw_affiliation_strings":["Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076462524","display_name":"Yingying Zhao","orcid":"https://orcid.org/0000-0001-5902-1306"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingying Zhao","raw_affiliation_strings":["Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075140549","display_name":"Hongbo Cao","orcid":"https://orcid.org/0000-0003-2128-6442"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbo Cao","raw_affiliation_strings":["Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123374478","display_name":"Baomin Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baomin Xu","raw_affiliation_strings":["Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Big Data and Artificial Intelligence in Transportation, Ministry of Education, and the School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5048347888"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16296162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":null,"first_page":"1142","last_page":"1154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.32519999146461487,"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":0.32519999146461487,"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":0.1396999955177307,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.0989999994635582,"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":0.9955999851226807},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6654000282287598},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5590999722480774},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5368000268936157},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5157999992370605},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5113000273704529},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.501800000667572},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4715000092983246},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.45399999618530273}],"concepts":[{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.9955999851226807},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8440999984741211},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6654000282287598},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5590999722480774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5562999844551086},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5368000268936157},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5157999992370605},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5113000273704529},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.501800000667572},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4860000014305115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4733999967575073},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4715000092983246},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.45399999618530273},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4108999967575073},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3057999908924103},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.2705000042915344}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tifs.2026.3655920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2026.3655920","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7564601898193359,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1896424170","https://openalex.org/W2117130368","https://openalex.org/W2117876524","https://openalex.org/W2194775991","https://openalex.org/W2251324968","https://openalex.org/W2798441115","https://openalex.org/W2798626461","https://openalex.org/W2942091739","https://openalex.org/W2962783375","https://openalex.org/W2962897020","https://openalex.org/W2963430933","https://openalex.org/W2963877604","https://openalex.org/W2966030703","https://openalex.org/W3109695251","https://openalex.org/W3138597937","https://openalex.org/W3141797743","https://openalex.org/W3198528147","https://openalex.org/W4213446860","https://openalex.org/W4387623677","https://openalex.org/W4390874351","https://openalex.org/W4393156872","https://openalex.org/W4393161237","https://openalex.org/W4401980693","https://openalex.org/W4407637752","https://openalex.org/W6940675582"],"related_works":[],"abstract_inverted_index":{"Backdoor":[0],"attacks":[1,59],"pose":[2],"severe":[3],"security":[4],"challenges":[5],"to":[6,11,45],"federated":[7,32,166],"learning":[8,106],"systems":[9],"due":[10],"their":[12],"stealthy":[13],"nature.":[14],"Existing":[15],"detection":[16,66,163,211],"methods":[17],"primarily":[18],"focus":[19],"on":[20,132,195],"identifying":[21],"anomalies":[22],"by":[23,109],"analyzing":[24],"discrepancies":[25],"in":[26,31,146],"client":[27,42,175],"model":[28,49],"updates.":[29],"However,":[30],"learning,":[33],"the":[34,54,63,87,92,97,128,144],"non-independent":[35],"and":[36,60,91,152,176,219],"identically":[37],"distributed":[38],"(non-IID)":[39],"nature":[40],"of":[41,57,65,216],"data":[43,220],"leads":[44],"inconsistencies":[46],"among":[47],"local":[48],"updates,":[50],"which":[51,71],"can":[52,100],"mask":[53],"distinguishing":[55],"features":[56],"backdoor":[58,93,162,186,217],"consequently":[61],"degrade":[62],"performance":[64,212],"methods.":[67],"Unlike":[68],"benign":[69,124,153,181],"models,":[70],"are":[72,82],"trained":[73],"solely":[74],"for":[75,85,165,173],"a":[76,104,137,160,214],"single":[77],"classification":[78,88],"task,":[79],"backdoored":[80,98,116,151],"models":[81,99,117,125,179],"simultaneously":[83],"optimized":[84],"both":[86],"(main)":[89],"task":[90],"task.":[94,130],"Therefore,":[95],"training":[96],"be":[101],"regarded":[102],"as":[103],"multi-task":[105],"problem.":[107],"Inspired":[108],"information":[110],"bottleneck":[111],"theory,":[112],"we":[113,135,158],"observe":[114],"that":[115,141,205],"exhibit":[118],"more":[119],"stable":[120],"feature":[121,147],"representations":[122],"than":[123],"when":[126],"performing":[127],"main":[129],"Based":[131],"this":[133,156],"insight,":[134],"propose":[136],"novel":[138],"stability":[139,149],"metric":[140],"quantitatively":[142],"captures":[143],"disparity":[145],"map":[148],"between":[150],"models.":[154],"Leveraging":[155],"metric,":[157],"develop":[159],"new":[161],"framework":[164],"learning.":[167],"Our":[168],"method":[169,207],"computes":[170],"anomaly":[171],"scores":[172],"each":[174],"selectively":[177],"aggregates":[178],"with":[180],"characteristics,":[182],"effectively":[183],"defending":[184],"against":[185],"attacks.":[187],"We":[188],"validate":[189],"our":[190,206],"approach":[191],"through":[192],"extensive":[193],"experiments":[194],"multiple":[196],"benchmark":[197],"datasets":[198],"under":[199],"non-IID":[200],"settings.":[201],"The":[202],"results":[203],"demonstrate":[204],"consistently":[208],"achieves":[209],"high":[210],"across":[213],"range":[215],"scenarios":[218],"heterogeneity":[221],"levels.":[222]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-01-21T00:00:00"}