{"id":"https://openalex.org/W4416034136","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.960","title":"Beneath the Facade: Probing Safety Vulnerabilities in LLMs via Auto-Generated Jailbreak Prompts","display_name":"Beneath the Facade: Probing Safety Vulnerabilities in LLMs via Auto-Generated Jailbreak Prompts","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034136","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.960"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.960","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.960","pdf_url":"https://aclanthology.org/2025.findings-emnlp.960.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.960.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104239678","display_name":"Heehyeon Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heehyeon Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kyeongryul Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyeongryul Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090741314","display_name":"Joyce Jiyoung Whang","orcid":"https://orcid.org/0000-0002-4773-3194"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joyce Jiyoung Whang","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40490623,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17668","last_page":"17700"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10734","display_name":"Information and Cyber Security","score":0.22619999945163727,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10734","display_name":"Information and Cyber Security","score":0.22619999945163727,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.10840000212192535,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.08020000159740448,"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/vulnerability","display_name":"Vulnerability (computing)","score":0.41190001368522644},{"id":"https://openalex.org/keywords/risk-management","display_name":"Risk management","score":0.2888999879360199},{"id":"https://openalex.org/keywords/government","display_name":"Government (linguistics)","score":0.2728999853134155},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.2630999982357025},{"id":"https://openalex.org/keywords/risk-assessment","display_name":"Risk assessment","score":0.2563000023365021}],"concepts":[{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5250999927520752},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.43849998712539673},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.33000001311302185},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.29429998993873596},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.27630001306533813},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.960","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.960","pdf_url":"https://aclanthology.org/2025.findings-emnlp.960.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:koasas.kaist.ac.kr:10203/335493","is_oa":false,"landing_page_url":"http://hdl.handle.net/10203/335493","pdf_url":null,"source":{"id":"https://openalex.org/S4306402435","display_name":"KAIST Institutional Repository (KAIST)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157485424","host_organization_name":"Korea Advanced Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I157485424"],"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":"Conference"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.960","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.960","pdf_url":"https://aclanthology.org/2025.findings-emnlp.960.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":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1630947553","display_name":null,"funder_award_id":"RS-2022-II220369","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G3996153573","display_name":null,"funder_award_id":"RS-2022-II220369","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034136.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"proliferation":[2],"of":[3,22,37,48,91],"large":[4],"language":[5],"models":[6,10],"and":[7,46,97],"multimodal":[8,101],"generative":[9],"has":[11],"raised":[12],"concerns":[13],"about":[14],"their":[15],"potential":[16],"vulnerabilities":[17,67],"to":[18,40,100,114],"a":[19,27,127],"wide":[20],"range":[21,90],"real-world":[23,49],"safety":[24,110],"risks.":[25],"However,":[26],"critical":[28],"gap":[29],"persists":[30],"in":[31],"systematic":[32],"assessment,":[33],"alongside":[34],"the":[35,44],"lack":[36],"evaluation":[38],"frameworks":[39],"keep":[41],"pace":[42],"with":[43],"breadth":[45],"variability":[47],"risk":[50],"factors.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55],"introduce":[56],"TroGEN,":[57],"an":[58,74,84,122],"automated":[59],"jailbreak":[60,71,95,139],"prompt":[61],"generation":[62],"framework":[63],"that":[64,87,106,117],"assesses":[65],"these":[66],"by":[68],"deriving":[69],"scenario-driven":[70],"prompts":[72],"using":[73],"adversarial":[75,115],"agent.":[76],"Moving":[77],"beyond":[78],"labor-intensive":[79],"dataset":[80],"construction,":[81],"TroGEN":[82,107],"features":[83],"extensible":[85],"design":[86],"covers":[88],"broad":[89],"risks,":[92],"supports":[93],"plug-and-play":[94],"strategies,":[96],"adapts":[98],"seamlessly":[99],"settings.":[102],"Experimental":[103],"results":[104],"demonstrate":[105],"effectively":[108],"uncovers":[109],"weaknesses,":[111],"revealing":[112],"susceptibilities":[113],"attacks":[116,133],"conceal":[118],"malicious":[119],"intent":[120],"beneath":[121],"apparently":[123],"benign":[124],"facade,":[125],"like":[126],"Trojan":[128],"horse.":[129],"Furthermore,":[130],"such":[131],"stealthy":[132],"exhibit":[134],"resilience":[135],"even":[136],"against":[137],"existing":[138],"defense":[140],"methods.":[141]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}