{"id":"https://openalex.org/W4415433599","doi":"https://doi.org/10.21437/interspeech.2025-172","title":"Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems","display_name":"Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433599","doi":"https://doi.org/10.21437/interspeech.2025-172"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-172","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.09204","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120093893","display_name":"Chin Yuen Kwok","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chin Yuen Kwok","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102941083","display_name":"Jia Qi Yip","orcid":"https://orcid.org/0000-0002-9896-9658"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Qi Yip","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120093895","display_name":"Zhen Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhen Qiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120093896","display_name":"Chi Hung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chi Hung Chi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5120093897","display_name":"Kwok Yan Lam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kwok Yan Lam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2230","last_page":"2234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9390000104904175,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9390000104904175,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/interpretability","display_name":"Interpretability","score":0.8931999802589417},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7457000017166138},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.583299994468689},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5486999750137329},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4372999966144562},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.37529999017715454},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3328000009059906}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8931999802589417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476999759674072},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7457000017166138},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.583299994468689},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5486999750137329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5031999945640564},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42239999771118164},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34369999170303345},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3328000009059906},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3287000060081482},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.2549000084400177}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-172","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.09204","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.09204","pdf_url":"https://arxiv.org/pdf/2509.09204","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/202625","is_oa":true,"landing_page_url":"https://www.isca-archive.org/interspeech_2025/kwok25_interspeech.html#","pdf_url":"https://www.isca-archive.org/interspeech_2025/kwok25_interspeech.pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.09204","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.09204","pdf_url":"https://arxiv.org/pdf/2509.09204","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320325256","display_name":"Info-communications Media Development Authority","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415433599.pdf","grobid_xml":"https://content.openalex.org/works/W4415433599.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Audio":[0],"deepfake":[1],"detection":[2],"(ADD)":[3],"models":[4],"are":[5],"commonly":[6],"evaluated":[7],"using":[8],"datasets":[9,45,89],"that":[10,84],"combine":[11],"multiple":[12],"synthesizers,":[13],"with":[14,30],"performance":[15],"reported":[16],"as":[17],"a":[18,54,80,121],"single":[19,55],"Equal":[20],"Error":[21],"Rate":[22],"(EER).":[23],"However,":[24],"this":[25],"approach":[26,98],"disproportionately":[27],"weights":[28],"synthesizers":[29,112],"more":[31,94],"samples,":[32],"underrepresenting":[33],"others":[34],"and":[35,57,90,101,119],"reducing":[36],"the":[37],"overall":[38],"reliability":[39],"of":[40],"EER.":[41],"Additionally,":[42],"most":[43],"ADD":[44],"lack":[46],"diversity":[47],"in":[48],"bona":[49,77,87,115],"fide":[50,78,88,116],"speech,":[51],"often":[52],"featuring":[53],"environment":[56],"speech":[58,117],"style":[59],"(e.g.,":[60],"clean":[61],"read":[62],"speech),":[63],"limiting":[64],"their":[65],"ability":[66],"to":[67,104,124],"simulate":[68],"real-world":[69],"conditions.":[70],"To":[71],"address":[72],"these":[73],"challenges,":[74],"we":[75],"propose":[76],"cross-testing,":[79],"novel":[81],"evaluation":[82,106],"framework":[83],"incorporates":[85],"diverse":[86],"aggregates":[91],"EERs":[92],"for":[93],"balanced":[95],"assessments.":[96],"Our":[97],"improves":[99],"robustness":[100],"interpretability":[102],"compared":[103],"traditional":[105],"methods.":[107],"We":[108],"benchmark":[109],"over":[110],"150":[111],"across":[113],"nine":[114],"types":[118],"release":[120],"new":[122],"dataset":[123],"facilitate":[125],"further":[126],"research":[127],"at":[128],"https://github.com/cyaaronk/audio_deepfake_eval.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-23T00:00:00"}