{"id":"https://openalex.org/W7225619375","doi":"https://doi.org/10.21203/rs.3.rs-11257420/v1","title":"Multitask Deep Learning for Joint Deepfake Speech Detection and Spoofing Attack Attribution","display_name":"Multitask Deep Learning for Joint Deepfake Speech Detection and Spoofing Attack Attribution","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225619375","doi":"https://doi.org/10.21203/rs.3.rs-11257420/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11257420/v1","doi":"https://doi.org/10.21203/rs.3.rs-11257420/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11257420/v1","pdf_url":"https://www.researchsquare.com/article/rs-11257420/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-11257420/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161349277","display_name":"Abdulrahman Hussien","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170535673","display_name":"Sana'a University","ror":"https://ror.org/04hcvaf32","country_code":"YE","type":"education","lineage":["https://openalex.org/I170535673"]}],"countries":["YE"],"is_corresponding":false,"raw_author_name":"Abdulrahman Hussien","raw_affiliation_strings":["Sana\u2019a University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sana\u2019a University","institution_ids":["https://openalex.org/I170535673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161344638","display_name":"Ghaleb Aljafari","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170535673","display_name":"Sana'a University","ror":"https://ror.org/04hcvaf32","country_code":"YE","type":"education","lineage":["https://openalex.org/I170535673"]}],"countries":["YE"],"is_corresponding":false,"raw_author_name":"Ghaleb Aljafari","raw_affiliation_strings":["Sana\u2019a University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sana\u2019a University","institution_ids":["https://openalex.org/I170535673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076275091","display_name":"Mohammed Nasser Al-Andoli","orcid":"https://orcid.org/0000-0001-6491-9938","observed_orcids":["https://orcid.org/0000-0001-6491-9938"]},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Mohammed Nasser Al-Andoli","raw_affiliation_strings":["Multimedia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimedia University","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5161312201","display_name":"Malek Aljabri","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170535673","display_name":"Sana'a University","ror":"https://ror.org/04hcvaf32","country_code":"YE","type":"education","lineage":["https://openalex.org/I170535673"]}],"countries":["YE"],"is_corresponding":false,"raw_author_name":"Malek Aljabri","raw_affiliation_strings":["Sana\u2019a University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sana\u2019a University","institution_ids":["https://openalex.org/I170535673"]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9961000084877014,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9961000084877014,"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/T10828","display_name":"Biometric Identification and Security","score":0.001500000013038516,"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/T10860","display_name":"Speech and Audio Processing","score":0.0010000000474974513,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-deepfake-detection","display_name":"speech deepfake detection","score":0.9900000095367432},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.6790000200271606},{"id":"https://openalex.org/keywords/voice-spoofing","display_name":"voice spoofing","score":0.6579999923706055},{"id":"https://openalex.org/keywords/biometric-authentication-security","display_name":"biometric authentication security","score":0.6700000166893005},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"speech synthesis","score":0.382999986410141},{"id":"https://openalex.org/keywords/voice-conversion","display_name":"voice conversion","score":0.7269999980926514},{"id":"https://openalex.org/keywords/time-frequency-features","display_name":"time-frequency features","score":0.7059999704360962},{"id":"https://openalex.org/keywords/unseen-attack-generalization","display_name":"unseen attack generalization","score":0.7070000171661377},{"id":"https://openalex.org/keywords/acoustic-noise-robustness","display_name":"acoustic noise robustness","score":0.7749999761581421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8184000253677368},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7470999956130981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6819999814033508},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.6305999755859375},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.604200005531311},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.513700008392334},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5002999901771545},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4684999883174896},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46209999918937683},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.44589999318122864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4332999885082245},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.39149999618530273},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.36250001192092896},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.3050000071525574},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.29899999499320984},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11257420/v1","doi":"https://doi.org/10.21203/rs.3.rs-11257420/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11257420/v1","pdf_url":"https://www.researchsquare.com/article/rs-11257420/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11257420/v1","doi":"https://doi.org/10.21203/rs.3.rs-11257420/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11257420/v1","pdf_url":"https://www.researchsquare.com/article/rs-11257420/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225619375.pdf","grobid_xml":"https://content.openalex.org/works/W7225619375.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2131774270","https://openalex.org/W2148154194","https://openalex.org/W2158698691","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2295634712","https://openalex.org/W2588445447","https://openalex.org/W2590129515","https://openalex.org/W2890964092","https://openalex.org/W3026777299","https://openalex.org/W3128666957","https://openalex.org/W3200167423","https://openalex.org/W3201773091","https://openalex.org/W3211424380","https://openalex.org/W4293255030","https://openalex.org/W4297841787","https://openalex.org/W4381198892","https://openalex.org/W4412945512"],"related_works":["https://openalex.org/W4415433941","https://openalex.org/W4415332658","https://openalex.org/W4390523451","https://openalex.org/W7140167636","https://openalex.org/W7202189147","https://openalex.org/W4406316742","https://openalex.org/W4317181815","https://openalex.org/W7104033085","https://openalex.org/W7203461898","https://openalex.org/W4410145327"],"abstract_inverted_index":{"Abstract":[0],"The":[1,52],"rapid":[2],"advancement":[3],"of":[4,16,48,101,111],"neural":[5],"speech":[6,42],"synthesis":[7],"and":[8,25,44,61,68,78,105,122],"voice":[9],"conversion":[10],"technologies":[11],"has":[12],"increased":[13],"the":[14,83,94,126],"realism":[15],"synthetic":[17],"speech,":[18],"creating":[19],"significant":[20],"challenges":[21],"for":[22,145],"biometric":[23],"authentication":[24],"digital":[26],"forensics.":[27],"This":[28],"study":[29],"proposes":[30],"a":[31,65,69,90,97,106,142],"Multi-Task":[32],"Deep":[33],"Learning":[34],"(MT-DL)":[35],"framework":[36,53,95],"that":[37],"jointly":[38],"addresses":[39],"binary":[40,98],"deepfake":[41],"detection":[43,77,99],"supervised":[45,107],"spoof":[46,108],"attribution":[47,79,109],"known":[49,116],"attack":[50],"classes.":[51],"combines":[54],"complementary":[55],"spectro-temporal":[56],"representations":[57],"(MFCC,":[58],"Log-Mel":[59],"spectrograms,":[60],"delta-MFCC":[62],"features)":[63],"with":[64],"convolutional":[66],"front-end":[67],"hybrid":[70],"Bi-LSTM/Transformer":[71],"temporal":[72],"encoder":[73],"to":[74],"feed":[75],"task-specific":[76],"heads.":[80],"Evaluated":[81],"on":[82,125],"ASVspoof":[84],"2019":[85],"Logical":[86],"Access":[87],"dataset":[88,128],"using":[89],"stratified":[91],"60:40":[92],"split,":[93],"achieves":[96],"accuracy":[100,110],"99.75%":[102],"(0.48%":[103],"EER)":[104],"99.57%":[112],"(99.58%":[113],"Macro-F1)":[114],"across":[115],"attacks":[117,120],"(A01\u2013A06).":[118],"Unseen":[119],"(A07\u2013A19)":[121],"cross-dataset":[123],"evaluations":[124],"In-the-Wild":[127],"further":[129],"demonstrate":[130],"robust":[131],"generalization,":[132],"though":[133],"performance":[134],"sensitivity":[135],"under":[136],"severe":[137],"additive":[138],"acoustic":[139],"noise":[140],"remains":[141],"key":[143],"area":[144],"future":[146],"optimization.":[147]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}