{"id":"https://openalex.org/W4416249818","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228591","title":"Q-PGD: A Stealthy and Effective Speaker Recognition Adversarial Attacks Based on Quantized Projected Gradient Descent","display_name":"Q-PGD: A Stealthy and Effective Speaker Recognition Adversarial Attacks Based on Quantized Projected Gradient Descent","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416249818","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228591"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","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/A5090357947","display_name":"Jiahui Wang","orcid":"https://orcid.org/0000-0003-2552-0726"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiahui Wang","raw_affiliation_strings":["Xidian University,School of Cyber Engineering,Xian,China"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Cyber Engineering,Xian,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078593448","display_name":"Yulong Fu","orcid":"https://orcid.org/0000-0002-1778-4943"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulong Fu","raw_affiliation_strings":["Xidian University,School of Cyber Engineering,Xian,China"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Cyber Engineering,Xian,China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101197694","display_name":"Jincheng Yang","orcid":"https://orcid.org/0009-0002-2859-7921"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jincheng Yang","raw_affiliation_strings":["Xidian University,School of Cyber Engineering,Xian,China"],"affiliations":[{"raw_affiliation_string":"Xidian University,School of Cyber Engineering,Xian,China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090357947"],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19392531,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9628999829292297,"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":0.9628999829292297,"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/T12131","display_name":"Wireless Signal Modulation Classification","score":0.011099999770522118,"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":0.010700000450015068,"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/quantization","display_name":"Quantization (signal processing)","score":0.5985999703407288},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5845000147819519},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5511999726295471},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4456999897956848},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.44290000200271606},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41589999198913574},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.4018000066280365},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.39149999618530273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7394999861717224},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5985999703407288},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5845000147819519},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5770000219345093},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5511999726295471},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4456999897956848},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.4018000066280365},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3840999901294708},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32280001044273376},{"id":"https://openalex.org/C65856478","wikidata":"https://www.wikidata.org/wiki/Q3991682","display_name":"Attack model","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.314300000667572},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3005000054836273},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.29789999127388},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.28949999809265137},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2114925438","https://openalex.org/W2194775991","https://openalex.org/W2885918317","https://openalex.org/W2890964092","https://openalex.org/W2963857521","https://openalex.org/W2964077693","https://openalex.org/W3024869864","https://openalex.org/W3054852761","https://openalex.org/W3084424094","https://openalex.org/W3096023981","https://openalex.org/W3096614974","https://openalex.org/W3109668151","https://openalex.org/W3137249133","https://openalex.org/W3153453329","https://openalex.org/W3196368020","https://openalex.org/W3198162144","https://openalex.org/W3202281277","https://openalex.org/W4281951480","https://openalex.org/W4372340947","https://openalex.org/W4385823321"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,13,33,38,54,73,85,89,114,120,134,161,165,170],"widespread":[2],"adoption":[3],"of":[4],"Neural":[5],"Network":[6],"Model":[7],"in":[8,37],"Speaker":[9],"Recognition":[10],"Systems":[11],"(SRS),":[12],"vulnerability":[14],"caused":[15],"by":[16,53,113],"Adversarial":[17],"Attacks":[18],"poses":[19],"significant":[20],"security":[21],"concerns":[22],"recently.":[23],"However,":[24],"adversarial":[25],"attack":[26,63,128,135,145,168],"research":[27],"on":[28,32,43,66],"SRS":[29,150,172],"focuses":[30],"mainly":[31],"audio":[34,82],"signal":[35],"perturbation":[36],"time":[39,86],"domain,":[40,91],"while":[41],"studies":[42],"frequency-domain-based":[44],"attacks":[45],"still":[46],"remain":[47],"limited.":[48],"In":[49,156],"this":[50],"work,":[51],"inspired":[52],"MP3":[55],"compression":[56],"process,":[57],"we":[58],"proposed":[59,121,162],"a":[60,95,126,143],"frequency-domain":[61,103],"quantization":[62,97],"method":[64,122],"based":[65],"Projected":[67],"Gradient":[68],"Descent":[69],"(PGD),":[70],"which":[71],"leverages":[72],"(inverse)":[74],"Modified":[75],"Discrete":[76],"Cosine":[77],"Transform":[78],"(MDCT)":[79],"to":[80,88,99,158,169],"convert":[81],"signals":[83],"from":[84],"domain":[87],"frequency":[90],"and":[92,101,108],"iteratively":[93],"optimized":[94],"trainable":[96],"table":[98],"compress":[100],"manipulate":[102],"magnitudes.":[104],"For":[105],"both":[106],"closed":[107],"open":[109],"data":[110],"sets":[111],"used":[112],"current":[115],"mainstream":[116],"speaker":[117],"recognition":[118],"models,":[119],"not":[123],"only":[124],"achieved":[125],"100%":[127],"success":[129,146],"rate":[130,147],"but":[131],"also":[132],"made":[133],"process":[136],"more":[137],"stealthy.":[138],"Meanwhile,":[139],"it":[140],"can":[141],"maintain":[142],"high":[144],"even":[148],"against":[149],"equipped":[151],"with":[152],"transformation-based":[153],"defense":[154],"mechanisms.":[155],"particular,":[157],"our":[159],"knowledge,":[160],"work":[163],"is":[164],"first":[166],"successful":[167],"Cam++":[171],"model.":[173]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}