{"id":"https://openalex.org/W4399695855","doi":"https://doi.org/10.48550/arxiv.2406.09321","title":"JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models","display_name":"JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models","publication_year":2024,"publication_date":"2024-06-13","ids":{"openalex":"https://openalex.org/W4399695855","doi":"https://doi.org/10.48550/arxiv.2406.09321"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.09321","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.09321","pdf_url":"https://arxiv.org/pdf/2406.09321","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.09321","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101379650","display_name":"Delong Ran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ran, Delong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675904","display_name":"Jinyuan Liu","orcid":"https://orcid.org/0000-0003-2085-2676"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jinyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111170519","display_name":"Yichen Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Yichen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099137411","display_name":"Jingyi Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Jingyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113028838","display_name":"Xinlei He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Xinlei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099137412","display_name":"Tianshuo Cong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong, Tianshuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Wang, Anyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Anyu","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12268","display_name":"Deception detection and forensic psychology","score":0.9379000067710876,"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"}},"topics":[{"id":"https://openalex.org/T12268","display_name":"Deception detection and forensic psychology","score":0.9379000067710876,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5557085871696472}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5557085871696472}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.09321","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.09321","pdf_url":"https://arxiv.org/pdf/2406.09321","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.09321","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.09321","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.09321","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.09321","pdf_url":"https://arxiv.org/pdf/2406.09321","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399695855.pdf","grobid_xml":"https://content.openalex.org/works/W4399695855.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Jailbreak":[0],"attacks":[1,19,80],"induce":[2],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"to":[7,34,153,169],"generate":[8],"harmful":[9],"responses,":[10],"posing":[11],"severe":[12],"misuse":[13],"threats.":[14],"Though":[15],"research":[16,100,180],"on":[17,28],"jailbreak":[18,92,99,115,144,179,187],"and":[20,52,65,77,81,105,123,181],"defenses":[21],"is":[22,25],"emerging,":[23],"there":[24],"no":[26],"consensus":[27],"evaluating":[29,143],"jailbreaks,":[30],"i.e.,":[31],"the":[32,36,63,127,175,190],"methods":[33,76],"assess":[35],"harmfulness":[37],"of":[38,50,91,114,130],"an":[39,183],"LLM's":[40],"response":[41],"are":[42],"varied.":[43],"Each":[44],"approach":[45],"has":[46],"its":[47],"own":[48],"set":[49],"strengths":[51,122],"weaknesses,":[53,124],"impacting":[54],"their":[55,121,131],"alignment":[56],"with":[57,126,156],"human":[58],"values,":[59],"as":[60,62],"well":[61],"time":[64],"financial":[66],"cost.":[67],"This":[68],"diversity":[69],"challenges":[70],"researchers":[71],"in":[72,178],"choosing":[73],"suitable":[74],"evaluation":[75,93,162,176,188],"comparing":[78],"different":[79],"defenses.":[82],"In":[83,164],"this":[84],"paper,":[85],"we":[86,137,166],"conduct":[87],"a":[88,111,140,157,171],"comprehensive":[89],"analysis":[90],"methodologies,":[94],"drawing":[95],"from":[96],"nearly":[97],"90":[98],"published":[101],"between":[102],"May":[103],"2023":[104],"April":[106],"2024.":[107],"Our":[108],"study":[109],"introduces":[110],"systematic":[112],"taxonomy":[113],"evaluators,":[116],"offering":[117],"indepth":[118],"insights":[119],"into":[120],"along":[125],"current":[128],"status":[129],"adaptation.":[132],"To":[133],"aid":[134],"further":[135],"research,":[136],"propose":[138],"JailbreakEval,":[139],"toolkit":[141],"for":[142,186],"attempts.":[145],"JailbreakEval":[146,168],"includes":[147],"various":[148],"evaluators":[149],"out-of-the-box,":[150],"enabling":[151],"users":[152],"obtain":[154],"results":[155],"single":[158],"command":[159],"or":[160],"customized":[161],"workflows.":[163],"summary,":[165],"regard":[167],"be":[170],"catalyst":[172],"that":[173],"simplifies":[174],"process":[177],"fosters":[182],"inclusive":[184],"standard":[185],"within":[189],"community.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
