{"id":"https://openalex.org/W4391021696","doi":"https://doi.org/10.1109/asru57964.2023.10389650","title":"Clustering Unsupervised Representations as Defense Against Poisoning Attacks on Speech Commands Classification System","display_name":"Clustering Unsupervised Representations as Defense Against Poisoning Attacks on Speech Commands Classification System","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021696","doi":"https://doi.org/10.1109/asru57964.2023.10389650"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389650","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2606.28953","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040324682","display_name":"Thomas Thebaud","orcid":"https://orcid.org/0000-0001-8953-7872"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Thebaud","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052564654","display_name":"Sonal Joshi","orcid":"https://orcid.org/0000-0001-8020-7551"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sonal Joshi","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087010196","display_name":"Henry Li","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henry Li","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083770127","display_name":"Martin Sustek","orcid":"https://orcid.org/0000-0003-2351-6774"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ","US"],"is_corresponding":false,"raw_author_name":"Martin Sustek","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,USA","Faculty of Information Technology, Brno University of Technology, Czechia","Center for Language and Speech Processing, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Faculty of Information Technology, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jes\u00fas Villalba","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"abs/2010.10682","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":0.9991000294685364,"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":0.9991000294685364,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.986299991607666,"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/computer-science","display_name":"Computer science","score":0.7429180145263672},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.71872878074646},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.678260326385498},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5503498911857605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.424483060836792},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42270779609680176},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.42109888792037964},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36232423782348633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7429180145263672},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.71872878074646},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.678260326385498},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5503498911857605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.424483060836792},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42270779609680176},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.42109888792037964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36232423782348633}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/asru57964.2023.10389650","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2606.28953","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.28953","pdf_url":"https://arxiv.org/pdf/2606.28953","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":"doi:10.48550/arxiv.2606.28953","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.28953","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:2606.28953","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.28953","pdf_url":"https://arxiv.org/pdf/2606.28953","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1908991523","https://openalex.org/W1945616565","https://openalex.org/W1977556410","https://openalex.org/W2051267297","https://openalex.org/W2112507308","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2468716020","https://openalex.org/W2535690855","https://openalex.org/W2591602089","https://openalex.org/W2696967604","https://openalex.org/W2751936342","https://openalex.org/W2753783305","https://openalex.org/W2774423163","https://openalex.org/W2797583228","https://openalex.org/W2896457183","https://openalex.org/W2898759955","https://openalex.org/W2962763344","https://openalex.org/W2963888996","https://openalex.org/W2973049979","https://openalex.org/W2973252307","https://openalex.org/W3093678678","https://openalex.org/W3098643042","https://openalex.org/W3128839796","https://openalex.org/W3135970545","https://openalex.org/W3153453329","https://openalex.org/W3159481202","https://openalex.org/W3163083600","https://openalex.org/W3204915839","https://openalex.org/W4206979815","https://openalex.org/W4281951480","https://openalex.org/W4289300166","https://openalex.org/W4290712827","https://openalex.org/W4293846201","https://openalex.org/W4297676686","https://openalex.org/W4385080316","https://openalex.org/W6628547770","https://openalex.org/W6631190155","https://openalex.org/W6640425456","https://openalex.org/W6675022971","https://openalex.org/W6676935882","https://openalex.org/W6688816777","https://openalex.org/W6734354522","https://openalex.org/W6739088070","https://openalex.org/W6739868092","https://openalex.org/W6746897123","https://openalex.org/W6750665317","https://openalex.org/W6755207826","https://openalex.org/W6756074407","https://openalex.org/W6756333562","https://openalex.org/W6784805876","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W2110028391","https://openalex.org/W54497855","https://openalex.org/W217960748","https://openalex.org/W3125814499","https://openalex.org/W2090827041","https://openalex.org/W2094012830","https://openalex.org/W187246281","https://openalex.org/W2079194830"],"abstract_inverted_index":{"Poisoning":[0],"attacks":[1],"entail":[2],"attackers":[3],"intentionally":[4],"tampering":[5],"with":[6,74,102],"training":[7,85,111],"data.":[8],"In":[9],"this":[10],"paper,":[11],"we":[12,71,88,98,122],"consider":[13],"a":[14,20,43,63,117,124,139],"dirty-label":[15],"poisoning":[16],"attack":[17,127],"scenario":[18],"on":[19,45],"speech":[21],"commands":[22],"classification":[23],"system.":[24],"The":[25],"threat":[26,142],"model":[27],"assumes":[28],"that":[29],"certain":[30],"utterances":[31,101],"from":[32,130],"one":[33],"of":[34,141],"the":[35,57,84,100,103,114],"classes":[36],"(source":[37],"class)":[38],"are":[39],"poisoned":[40,119],"by":[41,56],"superimposing":[42],"trigger":[44,153],"it,":[46],"and":[47,91,112,147],"its":[48],"label":[49,106],"is":[50],"changed":[51],"to":[52,78,93,132],"another":[53],"class":[54],"selected":[55],"attacker":[58],"(target":[59],"class).":[60],"We":[61,134],"propose":[62],"filtering":[64],"defense":[65,137],"against":[66,138],"such":[67],"an":[68],"attack.":[69],"First,":[70],"use":[72,89],"DIstillation":[73],"NO":[75],"labels":[76],"(DINO)":[77],"learn":[79],"unsupervised":[80],"representations":[81],"for":[82,110],"all":[83],"examples.":[86],"Next,":[87],"K-means":[90],"LDA":[92],"cluster":[94,109],"these":[95],"representations.":[96],"Finally,":[97],"keep":[99],"most":[104],"repeated":[105],"in":[107,126],"their":[108],"discard":[113],"rest.":[115],"For":[116],"10%":[118],"source":[120,148],"class,":[121],"demonstrate":[123],"drop":[125],"success":[128],"rate":[129],"99.75%":[131],"0.25%.":[133],"test":[135],"our":[136],"variety":[140],"models,":[143],"including":[144],"different":[145],"target":[146],"classes,":[149],"as":[150,152],"well":[151],"variations.":[154]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}