{"id":"https://openalex.org/W4406458169","doi":"https://doi.org/10.1109/bigdata62323.2024.10825802","title":"Are Existing Large Language Models Robust Against Jailbreak Attacks?","display_name":"Are Existing Large Language Models Robust Against Jailbreak Attacks?","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406458169","doi":"https://doi.org/10.1109/bigdata62323.2024.10825802"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","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/A5114494284","display_name":"Baha Rababah","orcid":null},"institutions":[{"id":"https://openalex.org/I46247651","display_name":"University of Manitoba","ror":"https://ror.org/02gfys938","country_code":"CA","type":"education","lineage":["https://openalex.org/I46247651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Baha Rababah","raw_affiliation_strings":["University of Manitoba,Department of Computer Science,Winnipeg,Canada"],"affiliations":[{"raw_affiliation_string":"University of Manitoba,Department of Computer Science,Winnipeg,Canada","institution_ids":["https://openalex.org/I46247651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103451336","display_name":"She\u2010Ching Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I46247651","display_name":"University of Manitoba","ror":"https://ror.org/02gfys938","country_code":"CA","type":"education","lineage":["https://openalex.org/I46247651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shang Tommy Wu","raw_affiliation_strings":["University of Manitoba,Department of Computer Science,Winnipeg,Canada"],"affiliations":[{"raw_affiliation_string":"University of Manitoba,Department of Computer Science,Winnipeg,Canada","institution_ids":["https://openalex.org/I46247651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013014004","display_name":"Matthew Kwiatkowski","orcid":null},"institutions":[{"id":"https://openalex.org/I46247651","display_name":"University of Manitoba","ror":"https://ror.org/02gfys938","country_code":"CA","type":"education","lineage":["https://openalex.org/I46247651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Matthew Kwiatkowski","raw_affiliation_strings":["University of Manitoba,Department of Computer Science,Winnipeg,Canada"],"affiliations":[{"raw_affiliation_string":"University of Manitoba,Department of Computer Science,Winnipeg,Canada","institution_ids":["https://openalex.org/I46247651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016113718","display_name":"Carson K. Leung","orcid":"https://orcid.org/0000-0002-7541-9127"},"institutions":[{"id":"https://openalex.org/I46247651","display_name":"University of Manitoba","ror":"https://ror.org/02gfys938","country_code":"CA","type":"education","lineage":["https://openalex.org/I46247651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Carson K. Leung","raw_affiliation_strings":["University of Manitoba,Department of Computer Science,Winnipeg,Canada"],"affiliations":[{"raw_affiliation_string":"University of Manitoba,Department of Computer Science,Winnipeg,Canada","institution_ids":["https://openalex.org/I46247651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045418504","display_name":"C\u00fcneyt G\u00fcrcan Ak\u00e7ora","orcid":"https://orcid.org/0000-0002-2882-6950"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cuneyt Gurcan Akcora","raw_affiliation_strings":["University of Central Florida,AI Initiative,Orlando,FL,USA"],"affiliations":[{"raw_affiliation_string":"University of Central Florida,AI Initiative,Orlando,FL,USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5114494284"],"corresponding_institution_ids":["https://openalex.org/I46247651"],"apc_list":null,"apc_paid":null,"fwci":1.3817,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85386318,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5383","last_page":"5391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9947999715805054,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9947999715805054,"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/T12268","display_name":"Deception detection and forensic psychology","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.991599977016449,"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":0.706483781337738},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.42273804545402527}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.706483781337738},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.42273804545402527}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825802","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825802","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.49000000953674316}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311952","display_name":"University of Manitoba","ror":"https://ror.org/02gfys938"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W4378506863","https://openalex.org/W4386033770","https://openalex.org/W4387635776","https://openalex.org/W4387806231","https://openalex.org/W4387913685","https://openalex.org/W4388049829","https://openalex.org/W4388108510","https://openalex.org/W4389519817","https://openalex.org/W4389724183","https://openalex.org/W4391421099","https://openalex.org/W4392669753","https://openalex.org/W4399801327","https://openalex.org/W4405181600","https://openalex.org/W6809646742","https://openalex.org/W6853219528","https://openalex.org/W6857257659"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"safety":[1,118],"and":[2,35,48,85,115],"robustness":[3],"of":[4,52],"Large":[5],"Language":[6],"Models":[7],"(LLMs)":[8],"are":[9],"major":[10],"challenges":[11],"in":[12],"developing":[13],"generative":[14],"AI":[15],"applications.":[16,38],"One":[17],"key":[18],"issue":[19],"is":[20],"the":[21,50],"vulnerability":[22],"to":[23,32,90],"prompt":[24],"jailbreak":[25,77],"attacks,":[26],"which":[27],"pose":[28],"a":[29,44,67],"significant":[30],"threat":[31],"building":[33],"secure":[34],"resilient":[36],"LLM-based":[37],"In":[39],"this":[40],"work,":[41],"we":[42,65,94],"present":[43],"framework":[45],"for":[46],"understanding":[47],"evaluating":[49],"behaviors":[51],"popular":[53,99],"LLMs":[54,100],"by":[55,75],"categorizing":[56],"their":[57],"responses":[58],"into":[59,79,109],"five":[60],"distinct":[61],"exposure":[62],"levels.":[63],"Additionally,":[64],"introduce":[66],"novel":[68],"language":[69],"attack":[70],"that":[71,96],"circumvents":[72],"LLMs\u2019":[73,92,110],"defenses":[74],"translating":[76],"prompts":[78],"languages":[80],"such":[81],"as":[82],"Arabic,":[83],"Chinese,":[84],"Greek.":[86],"Despite":[87],"ongoing":[88],"efforts":[89],"enhance":[91],"safety,":[93],"find":[95],"nearly":[97],"all":[98],"can":[101],"be":[102],"jailbroken.":[103],"Our":[104],"findings":[105],"offer":[106],"detailed":[107],"insights":[108],"behavior,":[111],"improve":[112],"diagnostic":[113],"capabilities,":[114],"support":[116],"targeted":[117],"improvements.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}
