{"id":"https://openalex.org/W4414945417","doi":"https://doi.org/10.1145/3746265.3759675","title":"SASDN: A Generalizable and Minimal-Intervention LLM-Integrated Framework for Continual Adaptation in Spoofed Speech Detection","display_name":"SASDN: A Generalizable and Minimal-Intervention LLM-Integrated Framework for Continual Adaptation in Spoofed Speech Detection","publication_year":2025,"publication_date":"2025-10-08","ids":{"openalex":"https://openalex.org/W4414945417","doi":"https://doi.org/10.1145/3746265.3759675"},"language":"en","primary_location":{"id":"doi:10.1145/3746265.3759675","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746265.3759675","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st on Deepfake Forensics Workshop: Detection, Attribution, Recognition, and Adversarial Challenges in the Era of AI-Generated Media","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746265.3759675","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106801254","display_name":"Utkarsh Venaik","orcid":"https://orcid.org/0009-0002-2804-3195"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Utkarsh Venaik","raw_affiliation_strings":["IIIT Delhi, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"IIIT Delhi, New Delhi, India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104312388","display_name":"Akash Kushwaha","orcid":null},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Akash Kushwaha","raw_affiliation_strings":["IIIT Delhi, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"IIIT Delhi, New Delhi, India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093818585","display_name":"Nabeel Koya A","orcid":null},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nabeel Koya A","raw_affiliation_strings":["CDAC, Thiruvananthapuram, India"],"affiliations":[{"raw_affiliation_string":"CDAC, Thiruvananthapuram, India","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079357056","display_name":"Rajiv Ratn Shah","orcid":"https://orcid.org/0000-0003-1028-9373"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]},{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajiv Ratn Shah","raw_affiliation_strings":["IIIT Delhi, New Delhi, India"],"affiliations":[{"raw_affiliation_string":"IIIT Delhi, New Delhi, India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5106801254"],"corresponding_institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15318317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"93","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9847999811172485,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.8465999960899353},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6215000152587891},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5863000154495239},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.43709999322891235},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4325999915599823},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34779998660087585},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.32510000467300415},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3138999938964844}],"concepts":[{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.8465999960899353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7427999973297119},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6215000152587891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5874000191688538},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5863000154495239},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5645999908447266},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46459999680519104},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3138999938964844},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.3061000108718872},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.2773999869823456},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26930001378059387},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746265.3759675","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746265.3759675","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st on Deepfake Forensics Workshop: Detection, Attribution, Recognition, and Adversarial Challenges in the Era of AI-Generated Media","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746265.3759675","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746265.3759675","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st on Deepfake Forensics Workshop: Detection, Attribution, Recognition, and Adversarial Challenges in the Era of AI-Generated Media","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2112606109","https://openalex.org/W2123299109","https://openalex.org/W2176804518","https://openalex.org/W2194775991","https://openalex.org/W2588445447","https://openalex.org/W2590129515","https://openalex.org/W2790784932","https://openalex.org/W2807325376","https://openalex.org/W2808631503","https://openalex.org/W2902572801","https://openalex.org/W2972909277","https://openalex.org/W3024869864","https://openalex.org/W3026777299","https://openalex.org/W3040472729","https://openalex.org/W3096084197","https://openalex.org/W3097670835","https://openalex.org/W3200167423","https://openalex.org/W4381198892","https://openalex.org/W4385571829"],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"rise":[2],"of":[3,101],"generative":[4],"AI":[5],"(Gen-AI)":[6],"technologies":[7],"has":[8],"escalated":[9],"spoofing":[10],"risks":[11],"for":[12],"automatic":[13],"speaker":[14],"verification":[15],"(ASV)":[16],"systems.":[17],"Tra-":[18],"ditional":[19],"acoustic-only":[20],"methods":[21],"often":[22],"fail":[23],"when":[24],"faced":[25],"with":[26,42,105],"unseen":[27],"or":[28],"sophisticated":[29],"attacks.":[30],"We":[31],"propose":[32],"the":[33,91,110,123,129,136,154],"Semantic-Aided":[34],"Spoofing":[35],"Detection":[36],"Network":[37],"(SASDN),":[38],"which":[39],"augments":[40],"RawNet2":[41],"large":[43],"language":[44],"model":[45,92],"(LLM)":[46],"support":[47],"at":[48],"inference":[49],"time":[50],"via":[51],"a":[52,56,70,84,99,146,164],"two-step":[53],"mechanism:":[54],"(1)":[55],"learned":[57],"embedding":[58],"space":[59],"formed":[60],"during":[61],"training,":[62],"and":[63,121],"(2)":[64],"final":[65],"score":[66],"fusion":[67],"weighted":[68],"by":[69,97],"tunable":[71],"factor":[72],"\u03b4.":[73],"Rather":[74],"than":[75],"relying":[76],"on":[77,145],"complex":[78],"multi-modal":[79],"training":[80],"pipelines,":[81],"SASDN":[82,133,152],"incorporates":[83],"novel":[85],"label":[86],"impurity":[87],"strategy":[88],"that":[89,151],"conditions":[90],"to":[93,118,135,161],"accept":[94],"uncertain":[95],"supervision":[96],"substituting":[98],"fraction":[100],"ground":[102],"truth":[103],"labels":[104],"''Don't":[106],"Know.''":[107],"At":[108],"inference,":[109],"LLM":[111,130],"evaluates":[112],"transcribed":[113],"speech":[114],"against":[115,168],"external":[116],"knowledge":[117],"verify":[119],"authenticity":[120],"adjusts":[122],"ASV":[124],"model's":[125],"prediction":[126],"accordingly.":[127],"If":[128],"is":[131],"uncertain,":[132],"reverts":[134],"original":[137],"acoustic":[138],"classification,":[139],"ensuring":[140],"no":[141],"performance":[142],"degradation.":[143],"Evaluations":[144],"VoxCeleb2-derived":[147],"spoofed":[148],"dataset":[149],"demonstrate":[150],"reduces":[153],"equal":[155],"error":[156],"rate":[157],"(EER)":[158],"from":[159],"22.71%":[160],"6.5%,":[162],"offering":[163],"continually":[165],"adaptive":[166],"defense":[167],"emerging":[169],"threats.":[170]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}