{"id":"https://openalex.org/W4391021448","doi":"https://doi.org/10.1109/asru57964.2023.10389697","title":"Joint Energy-Based Model for Robust Speech Classification System Against Dirty-Label Backdoor Poisoning Attacks","display_name":"Joint Energy-Based Model for Robust Speech Classification System Against Dirty-Label Backdoor Poisoning Attacks","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021448","doi":"https://doi.org/10.1109/asru57964.2023.10389697"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389697","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389697","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":["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/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,Baltimore,MD,USA","Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","Faculty of Information Technology, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, 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"]}]},{"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,Baltimore,MD,USA","Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, 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,Baltimore,MD,USA","Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","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,Baltimore,MD,USA","Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, 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,Baltimore,MD,USA","Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, 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,Baltimore,MD,USA","Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, 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,Baltimore,MD,USA","Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, 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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"30","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":0.9950000047683716,"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":0.9950000047683716,"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":0.9926999807357788,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9921000003814697,"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/backdoor","display_name":"Backdoor","score":0.7958616018295288},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7950608134269714},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6537668108940125},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5282596349716187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5028831362724304},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4851273000240326},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.48379606008529663},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46930932998657227},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4587045907974243},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4141029119491577},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.29459041357040405},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.26609349250793457},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.14013981819152832},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08617553114891052},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07015368342399597}],"concepts":[{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.7958616018295288},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7950608134269714},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6537668108940125},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5282596349716187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5028831362724304},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4851273000240326},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.48379606008529663},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46930932998657227},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4587045907974243},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4141029119491577},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.29459041357040405},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26609349250793457},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.14013981819152832},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08617553114891052},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07015368342399597},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389697","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389697","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2194775991","https://openalex.org/W2473930607","https://openalex.org/W2560674852","https://openalex.org/W2765325683","https://openalex.org/W2788388592","https://openalex.org/W2797583228","https://openalex.org/W2898759955","https://openalex.org/W2942091739","https://openalex.org/W2963888996","https://openalex.org/W2964137095","https://openalex.org/W3007358161","https://openalex.org/W3117572899","https://openalex.org/W3128839796","https://openalex.org/W3162804012","https://openalex.org/W3209819950","https://openalex.org/W4297676686","https://openalex.org/W4323697643","https://openalex.org/W4382119306","https://openalex.org/W6630632610","https://openalex.org/W6679728604","https://openalex.org/W6684809622","https://openalex.org/W6739088070","https://openalex.org/W6750665317","https://openalex.org/W6756074407","https://openalex.org/W6756333562","https://openalex.org/W6771731465","https://openalex.org/W6774126473","https://openalex.org/W6774177702","https://openalex.org/W6780123631","https://openalex.org/W6791834630","https://openalex.org/W6810206781","https://openalex.org/W6851077928"],"related_works":["https://openalex.org/W2093104230","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W2128027845","https://openalex.org/W4386184937","https://openalex.org/W4394728283","https://openalex.org/W1493875009","https://openalex.org/W2105231718","https://openalex.org/W4388844349","https://openalex.org/W2019680624"],"abstract_inverted_index":{"Our":[0,23],"novel":[1],"technique":[2],"utilizes":[3],"a":[4,57,64,78,102,111],"Joint":[5],"Energy-based":[6],"Model":[7],"(JEM)":[8],"that":[9,128],"integrates":[10],"both":[11],"discriminative":[12,104],"and":[13],"generative":[14,79],"approaches":[15],"to":[16,55,115],"increase":[17],"resistance":[18,93,109],"against":[19],"dirty-label":[20],"backdoor":[21],"attacks.":[22],"approach":[24],"is":[25,31],"especially":[26],"effective":[27],"when":[28],"the":[29,38,41,60],"trigger":[30],"short":[32],"or":[33],"hardly":[34],"perceivable.":[35],"We":[36,120],"simulate":[37],"attack":[39],"on":[40],"Speech":[42],"Commands":[43],"Dataset":[44],"consisting":[45],"of":[46,59,81],"1s":[47],"audio":[48],"clips.":[49],"During":[50,69],"training,":[51],"we":[52,71],"use":[53],"JEM":[54,100,116,131,135],"model":[56,105],"view":[58],"input":[61],"implemented":[62],"by":[63,125],"randomly":[65],"selected":[66],"610ms":[67],"window.":[68],"inference,":[70],"combine":[72],"all":[73],"(40)":[74],"possible":[75],"views":[76],"utilizing":[77],"part":[80],"JEM.":[82],"The":[83],"resulting":[84],"system":[85],"has":[86],"slightly":[87],"decreased":[88],"accuracy":[89],"but":[90,117,132],"significantly":[91],"increased":[92,108],"shown":[94],"in":[95],"multiple":[96],"scenarios.":[97],"Interestingly,":[98],"replacing":[99],"with":[101,110],"standard":[103],"(Disc)":[106],"provides":[107],"lesser":[112],"effect":[113],"compared":[114],"maintains":[118],"accuracy.":[119],"introduce":[121],"an":[122],"extension":[123],"motivated":[124],"semi-supervised":[126],"training":[127],"further":[129],"improves":[130],"not":[133],"Disc.":[134],"can":[136],"also":[137],"benefit":[138],"from":[139],"Gaussian":[140],"noise":[141],"during":[142],"evaluation.":[143]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}