{"id":"https://openalex.org/W4416799690","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249352","title":"Neural Semi-Fragile Watermarking for Proactive Deepfake Speech Detection","display_name":"Neural Semi-Fragile Watermarking for Proactive Deepfake Speech Detection","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799690","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249352"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113141955","display_name":"Dohyun Yoon","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Dohyun Yoon","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006808971","display_name":"Tomoki Toda","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2092","last_page":"2097"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.41269999742507935,"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":0.41269999742507935,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.1826999932527542,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.12200000137090683,"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/digital-watermarking","display_name":"Digital watermarking","score":0.8690000176429749},{"id":"https://openalex.org/keywords/watermark","display_name":"Watermark","score":0.8073999881744385},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6401000022888184},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.6126000285148621},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5968999862670898},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.34860000014305115}],"concepts":[{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.8690000176429749},{"id":"https://openalex.org/C164112704","wikidata":"https://www.wikidata.org/wiki/Q7974348","display_name":"Watermark","level":3,"score":0.8073999881744385},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7588000297546387},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6401000022888184},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.6126000285148621},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5968999862670898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4925999939441681},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4661000072956085},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3133000135421753},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2780581891","wikidata":"https://www.wikidata.org/wiki/Q15738686","display_name":"Copy protection","level":4,"score":0.29409998655319214},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6791223834","display_name":null,"funder_award_id":"JPNP25006","funder_id":"https://openalex.org/F4320321034","funder_display_name":"New Energy and Industrial Technology Development Organization"}],"funders":[{"id":"https://openalex.org/F4320321034","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2045871908","https://openalex.org/W2141998673","https://openalex.org/W2150658333","https://openalex.org/W2593116425","https://openalex.org/W2593414223","https://openalex.org/W3024920698","https://openalex.org/W3102428524","https://openalex.org/W3127136277","https://openalex.org/W3142087749","https://openalex.org/W3197273793","https://openalex.org/W4200462593","https://openalex.org/W4225420087","https://openalex.org/W4294903856","https://openalex.org/W4313984387","https://openalex.org/W4323896824","https://openalex.org/W4372260053","https://openalex.org/W4381198892","https://openalex.org/W4385822463","https://openalex.org/W4392903621"],"related_works":[],"abstract_inverted_index":{"Proactive":[0],"methods":[1,34],"for":[2,73,114],"detecting":[3],"deepfake":[4,51,115],"speech,":[5],"which":[6,20],"utilize":[7],"audio":[8],"watermarks,":[9],"have":[10],"been":[11],"studied":[12],"as":[13],"an":[14],"alternative":[15],"to":[16,27,48,75,85,92,98],"passive":[17],"detection":[18,44],"methods,":[19],"are":[21,61,90],"generally":[22],"considered":[23],"weak":[24],"at":[25],"generalizing":[26,74],"unseen":[28],"spoofing":[29],"attacks.":[30],"However,":[31],"existing":[32],"proactive":[33],"focus":[35],"mainly":[36],"on":[37],"the":[38,50,55,58,83,93,109,112],"imperceptibility":[39],"of":[40,57,111],"watermarks":[41,88],"and":[42],"their":[43],"accuracy.":[45],"Consequently,":[46],"attempts":[47],"link":[49],"generation":[52,78,106],"process":[53,72],"with":[54],"training":[56],"watermarking":[59],"system":[60],"limited.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"introduce":[67],"a":[68],"novel":[69],"watermark":[70,94],"distortion":[71,95],"diverse":[76],"speech":[77,105,116],"systems.":[79],"This":[80],"approach":[81],"allows":[82],"method":[84,113],"generate":[86],"semi-fragile":[87],"that":[89],"vulnerable":[91],"but":[96],"robust":[97],"various":[99],"acoustic":[100],"distortions.":[101],"Experiments":[102],"using":[103],"open-source":[104],"systems":[107],"demonstrate":[108],"effectiveness":[110],"detection.":[117]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}
