{"id":"https://openalex.org/W7140085383","doi":"https://doi.org/10.18653/v1/2026.eacl-long.278","title":"Now You Hear Me: Audio Narrative Attacks Against Large Audio\u2013Language Models","display_name":"Now You Hear Me: Audio Narrative Attacks Against Large Audio\u2013Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140085383","doi":"https://doi.org/10.18653/v1/2026.eacl-long.278"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.278","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.278","pdf_url":"https://aclanthology.org/2026.eacl-long.278.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-long.278.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ye Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Haibo Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haibo Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yaoning Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaoning Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jun Zhuang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Zhuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Haohan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haohan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5925","last_page":"5939"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.3788999915122986,"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":0.3788999915122986,"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":0.11289999634027481,"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/T11309","display_name":"Music and Audio Processing","score":0.06310000270605087,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/narrative","display_name":"Narrative","score":0.5587999820709229},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2669999897480011},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2305999994277954}],"concepts":[{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.5587999820709229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5134999752044678},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3391000032424927},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.29089999198913574},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.2784999907016754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2775000035762787},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.23810000717639923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23250000178813934},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2305999994277954}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.278","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.278","pdf_url":"https://aclanthology.org/2026.eacl-long.278.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.278","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.278","pdf_url":"https://aclanthology.org/2026.eacl-long.278.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140085383.pdf","grobid_xml":"https://content.openalex.org/works/W7140085383.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"audio-language":[1],"models":[2],"increasingly":[3],"operate":[4],"on":[5],"raw":[6],"speech":[7],"inputs,":[8],"enabling":[9],"more":[10,126],"seamless":[11],"integration":[12],"across":[13],"domains":[14],"such":[15],"as":[16,122],"voice":[17],"assistants,":[18],"education,":[19],"and":[20,68,118],"clinical":[21],"triage.This":[22],"transition,":[23],"however,":[24],"introduces":[25],"a":[26,45,53,97],"distinct":[27],"class":[28],"of":[29,39],"vulnerabilities":[30],"that":[31,48,101,113],"remain":[32],"largely":[33],"uncharacterized.We":[34],"examine":[35],"the":[36,83,108],"security":[37],"implications":[38],"this":[40],"modality":[41],"shift":[42],"by":[43],"designing":[44],"text-to-audio":[46],"jailbreak":[47],"embeds":[49],"disallowed":[50],"directives":[51],"within":[52],"narrative-style":[54],"audio":[55],"stream.The":[56],"attack":[57],"leverages":[58],"an":[59],"advanced":[60],"instructionfollowing":[61],"text-to-speech":[62],"(TTS)":[63],"model":[64],"to":[65],"exploit":[66],"structural":[67],"acoustic":[69],"properties,":[70],"thereby":[71],"circumventing":[72],"safety":[73,111],"mechanisms":[74],"primarily":[75],"calibrated":[76],"for":[77,110],"text.When":[78],"delivered":[79],"through":[80],"synthetic":[81],"speech,":[82],"narrative":[84],"format":[85],"elicits":[86],"restricted":[87],"outputs":[88],"from":[89],"state-of-the-art":[90],"models,":[91],"including":[92],"Gemini":[93],"2.0":[94],"Flash,":[95],"achieving":[96],"98.26%":[98],"success":[99],"rate":[100],"substantially":[102],"exceeds":[103],"text-only":[104],"baselines.These":[105],"results":[106],"highlight":[107],"need":[109],"frameworks":[112],"jointly":[114],"reason":[115],"over":[116],"linguistic":[117],"paralinguistic":[119],"representations,":[120],"particularly":[121],"speech-based":[123],"interfaces":[124],"become":[125],"prevalent.":[127]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-04T00:00:00"}
