{"id":"https://openalex.org/W4415025845","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249120","title":"MDD: A Mask Diffusion Detector to Protect Speaker Verification Systems from Adversarial Perturbations","display_name":"MDD: A Mask Diffusion Detector to Protect Speaker Verification Systems from Adversarial Perturbations","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4415025845","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249120"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249120","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.19180","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027561341","display_name":"Yibo Bai","orcid":"https://orcid.org/0009-0007-1145-1391"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yibo Bai","raw_affiliation_strings":["EURECOM,Digital Security Department,France","Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EURECOM,Digital Security Department,France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031711236","display_name":"Sizhou Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sizhou Chen","raw_affiliation_strings":["School of Computer Science, The University of Sydney,Australia","The University of Sydney (New South Wales 2006 - Australia)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Sydney,Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"The University of Sydney (New South Wales 2006 - Australia)","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011500823","display_name":"Michele Panariello","orcid":"https://orcid.org/0009-0007-4154-5460"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Michele Panariello","raw_affiliation_strings":["EURECOM,Digital Security Department,France","Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EURECOM,Digital Security Department,France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University,China","China Telecom Corp Ltd (China)","Northwestern Polytechnical University [Xi'an] (6WV8+J5V, Beilin, Xi An Shi, Chine, 710071 - China)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"China Telecom Corp Ltd (China)","institution_ids":["https://openalex.org/I4210136246"]},{"raw_affiliation_string":"Northwestern Polytechnical University [Xi'an] (6WV8+J5V, Beilin, Xi An Shi, Chine, 710071 - China)","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049594655","display_name":"Massimiliano Todisco","orcid":"https://orcid.org/0000-0003-2883-0324"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Massimiliano Todisco","raw_affiliation_strings":["EURECOM,Digital Security Department,France","Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EURECOM,Digital Security Department,France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062177787","display_name":"Nicholas Evans","orcid":"https://orcid.org/0000-0003-0945-7747"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicholas Evans","raw_affiliation_strings":["EURECOM,Digital Security Department,France","Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EURECOM,Digital Security Department,France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"Eurecom [Sophia Antipolis] (Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex - France)","institution_ids":["https://openalex.org/I1902872"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14321815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"595","last_page":"600"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9690999984741211,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9690999984741211,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9351999759674072,"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/adversarial-system","display_name":"Adversarial system","score":0.7990000247955322},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6189000010490417},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.616100013256073},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5967000126838684},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5051000118255615},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5013999938964844},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4871000051498413},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.38769999146461487}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7990000247955322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7170000076293945},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6189000010490417},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.616100013256073},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5967000126838684},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5084999799728394},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5051000118255615},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5013999938964844},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4871000051498413},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38609999418258667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38280001282691956},{"id":"https://openalex.org/C2779079576","wikidata":"https://www.wikidata.org/wiki/Q17092823","display_name":"Jamming","level":2,"score":0.3707999885082245},{"id":"https://openalex.org/C2780909371","wikidata":"https://www.wikidata.org/wiki/Q4801092","display_name":"Artificial noise","level":4,"score":0.3546999990940094},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.326200008392334},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.30399999022483826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2653000056743622}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249120","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"},{"id":"pmh:oai:arXiv.org:2508.19180","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.19180","pdf_url":"https://arxiv.org/pdf/2508.19180","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05300065v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05300065","pdf_url":"https://hal.science/hal-05300065/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"APSIPA ASC 2025, 17th Asia Pacific Signal and Information Processing Association Annual Summit and Conference, IEEE, Oct 2025, Shangri-la, Singapore","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2508.19180","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.19180","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.19180","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.19180","pdf_url":"https://arxiv.org/pdf/2508.19180","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4053248193","display_name":"Privacy-preserving SPIKing nEural networks for automatic speaker verification","funder_award_id":"ANR-23-CE39-0005","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Speaker":[0],"verification":[1,119,144],"systems":[2],"are":[3],"increasingly":[4],"deployed":[5],"in":[6],"security-sensitive":[7],"applications":[8],"but":[9],"remain":[10],"highly":[11],"vulnerable":[12],"to":[13,46,121,124],"adversarial":[14,28,84,96],"perturbations.":[15],"In":[16],"this":[17],"work,":[18],"we":[19],"propose":[20],"the":[21,58,69,74,133],"Mask":[22],"Diffusion":[23],"Detector":[24],"(MDD),":[25],"a":[26,35,53],"novel":[27],"detection":[29,97],"and":[30,48,99,107,141],"purification":[31],"framework":[32],"based":[33],"on":[34,73],"text-conditioned":[36],"masked":[37],"diffusion":[38,55],"model.":[39],"During":[40],"training,":[41],"MDD":[42,80,93,112],"applies":[43],"partial":[44],"masking":[45,137],"Mel-spectrograms":[47],"progressively":[49],"adds":[50],"noise":[51],"through":[52],"forward":[54],"process,":[56],"simulating":[57],"degradation":[59],"of":[60,135],"clean":[61,70,128],"speech":[62],"features.":[63],"A":[64],"reverse":[65],"process":[66],"then":[67],"reconstructs":[68],"representation":[71],"conditioned":[72],"input":[75],"transcription.":[76],"Unlike":[77],"prior":[78,101],"approaches,":[79],"does":[81],"not":[82],"require":[83],"examples":[85],"or":[86],"large-scale":[87],"pretraining.":[88],"Experimental":[89],"results":[90],"show":[91],"that":[92],"achieves":[94],"strong":[95],"performance":[98,120],"outperforms":[100],"state-of-the-art":[102],"methods,":[103],"including":[104],"both":[105],"diffusionbased":[106],"neural":[108],"codec-based":[109],"approaches.":[110],"Furthermore,":[111],"effectively":[113],"purifies":[114],"adversarially-manipulated":[115],"speech,":[116],"restoring":[117],"speaker":[118,143],"levels":[122],"close":[123],"those":[125],"observed":[126],"under":[127],"conditions.":[129],"These":[130],"findings":[131],"demonstrate":[132],"potential":[134],"diffusion-based":[136],"strategies":[138],"for":[139],"secure":[140],"reliable":[142],"systems.":[145]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}
