{"id":"https://openalex.org/W7147083668","doi":"https://doi.org/10.1016/j.neucom.2026.133534","title":"A domain-based taxonomy of jailbreak vulnerabilities in large language models","display_name":"A domain-based taxonomy of jailbreak vulnerabilities in large language models","publication_year":2026,"publication_date":"2026-04-01","ids":{"openalex":"https://openalex.org/W7147083668","doi":"https://doi.org/10.1016/j.neucom.2026.133534"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2026.133534","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133534","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.neucom.2026.133534","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108162780","display_name":"Carlos Pel\u00e1ez-Gonz\u00e1lez","orcid":null},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Carlos Pel\u00e1ez-Gonz\u00e1lez","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, University of Granada, Avda. del Hospicio S/N, Granada, 18010, Granada, Spain"],"raw_orcid":"https://orcid.org/0000-0001-7976-3139","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, University of Granada, Avda. del Hospicio S/N, Granada, 18010, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128154547","display_name":"Andr\u00e9s Herrera-Poyatos","orcid":null},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Andr\u00e9s Herrera-Poyatos","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, University of Granada, Avda. del Hospicio S/N, Granada, 18010, Granada, Spain"],"raw_orcid":"https://orcid.org/0000-0001-9183-5262","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, University of Granada, Avda. del Hospicio S/N, Granada, 18010, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039025498","display_name":"Cristina Zuheros","orcid":"https://orcid.org/0000-0002-8213-3581"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Cristina Zuheros","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, University of Granada, Avda. del Hospicio S/N, Granada, 18010, Granada, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, University of Granada, Avda. del Hospicio S/N, Granada, 18010, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094255427","display_name":"David Herrera-Poyatos","orcid":null},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David Herrera-Poyatos","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, University of Granada, Avda. del Hospicio S/N, Granada, 18010, Granada, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, University of Granada, Avda. del Hospicio S/N, Granada, 18010, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119312245","display_name":"Virilo Tejedor","orcid":null},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Virilo Tejedor","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, University of Granada, Avda. del Hospicio S/N, Granada, 18010, Granada, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, University of Granada, Avda. del Hospicio S/N, Granada, 18010, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132630645","display_name":"Francisco Herrera","orcid":null},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Francisco Herrera","raw_affiliation_strings":["Department of Computer Science and Artificial Intelligence, University of Granada, Avda. del Hospicio S/N, Granada, 18010, Granada, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Artificial Intelligence, University of Granada, Avda. del Hospicio S/N, Granada, 18010, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5108162780"],"corresponding_institution_ids":["https://openalex.org/I173304897"],"apc_list":{"value":2470,"currency":"USD","value_usd":2470},"apc_paid":{"value":2470,"currency":"USD","value_usd":2470},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35736949,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"683","issue":null,"first_page":"133534","last_page":"133534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6287000179290771,"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":0.6287000179290771,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.1331000030040741,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.04659999907016754,"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/adversarial-system","display_name":"Adversarial system","score":0.7418000102043152},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7409999966621399},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.708299994468689},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5662000179290771},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5113999843597412},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4805999994277954},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44200000166893005},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.40380001068115234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8205999732017517},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7418000102043152},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7409999966621399},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.708299994468689},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5662000179290771},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5113999843597412},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4805999994277954},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.46209999918937683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4578000009059906},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3472999930381775},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C22680326","wikidata":"https://www.wikidata.org/wiki/Q7444867","display_name":"Secure coding","level":5,"score":0.2946000099182129},{"id":"https://openalex.org/C46355384","wikidata":"https://www.wikidata.org/wiki/Q726686","display_name":"Compromise","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C2780264999","wikidata":"https://www.wikidata.org/wiki/Q7445032","display_name":"Security domain","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.neucom.2026.133534","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133534","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.neucom.2026.133534","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133534","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6854330897331238,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327970","display_name":"Instituto Nacional de Ciberseguridad","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W4392353733","https://openalex.org/W4395034112","https://openalex.org/W4416822368"],"related_works":[],"abstract_inverted_index":{"The":[0,228],"study":[1],"of":[2,40,54,63,71,79,120,132,159,183,224,278,295,315],"large":[3],"language":[4,20],"models":[5],"(LLMs)":[6,207],"is":[7,97,230,245],"a":[8,68,98,156,164,225,233,253,268],"key":[9,189],"area":[10],"in":[11,75,89,130],"open-world":[12],"machine":[13],"learning.":[14],"Although":[15],"LLMs":[16,272],"demonstrate":[17],"remarkable":[18],"natural":[19],"processing":[21],"capabilities,":[22],"they":[23,137],"also":[24],"face":[25],"several":[26],"challenges,":[27],"including":[28],"consistency":[29],"issues,":[30],"hallucinations,":[31],"and":[32,66,92,113,123,174,247,287],"jailbreak":[33,64,72,128,184],"vulnerabilities.":[34,185],"Jailbreaking":[35],"refers":[36],"to":[37,47,126,210,218,270,307],"the":[38,52,61,76,104,118,133,180,222,250,257,263,303,316],"crafting":[39],"prompts":[41],"that":[42,50,108,142],"bypass":[43],"alignment":[44,83],"safeguards,":[45],"leading":[46],"unsafe":[48],"outputs":[49],"compromise":[51],"integrity":[53],"LLMs.":[55,80],"This":[56,115,243],"work":[57],"specifically":[58],"focuses":[59],"on":[60,100,146,201,262],"challenge":[62],"vulnerabilities":[65],"introduces":[67],"novel":[69],"taxonomy":[70,165,269],"attacks":[73,129,144,214,279,296],"grounded":[74],"training":[77,112,240],"domains":[78,107],"It":[81],"characterizes":[82],"failures":[84],"as":[85],"arising":[86],"from":[87,192,232,249],"gaps":[88],"generalization,":[90,169,284],"objectives,":[91,171],"robustness.":[93,289],"Our":[94],"primary":[95],"contribution":[96],"perspective":[99],"jailbreak,":[101],"framed":[102],"through":[103],"different":[105,239],"linguistic":[106],"emerge":[109],"during":[110],"LLM":[111,160,226,304],"alignment.":[114],"viewpoint":[116],"highlights":[117],"limitations":[119],"existing":[121],"approaches":[122],"enables":[124],"us":[125],"classify":[127,271],"terms":[131],"underlying":[134],"model":[135],"deficiencies":[136],"exploit.":[138],"Unlike":[139],"conventional":[140],"classifications":[141],"categorize":[143,292],"based":[145,246],"prompt":[147,151],"construction":[148],"methods":[149],"(e.g.,":[150],"templating),":[152],"our":[153,309],"approach":[154],"provides":[155],"deeper":[157],"understanding":[158],"behavior.":[161],"We":[162,197,290,300],"introduce":[163],"with":[166],"four":[167],"categories\u2014mismatched":[168],"competing":[170,285],"adversarial":[172,288],"robustness,":[173],"mixed":[175],"attacks\u2014":[176],"offering":[177],"insights":[178],"into":[179,297,313],"fundamental":[181],"nature":[182],"Finally,":[186],"we":[187,237,266,318],"present":[188],"lessons":[190],"derived":[191],"this":[193],"taxonomic":[194],"study.":[195],"\u2022":[196,260,299],"perform":[198],"an":[199,216],"analysis":[200,229,244],"why":[202],"aligned":[203],"Large":[204],"Language":[205],"Models":[206],"are":[208,280],"vulnerable":[209],"jailbreaking":[211,273,305],"attacks.":[212,274],"These":[213],"allows":[215],"user":[217],"generate":[219],"answers":[220],"against":[221],"policies":[223],"company.":[227],"done":[231],"domain":[234,241],"perspective,":[235],"where":[236],"distinguish":[238],"regions.":[242],"extended":[248],"Jailbroken":[251],"hypothesis,":[252],"paper":[254],"published":[255],"at":[256],"NeurIPS":[258],"conference.":[259],"Based":[261],"previous":[264],"analysis,":[265],"propose":[267],"Three":[275],"main":[276],"types":[277,294],"distinguished,":[281],"namely":[282],"mismatched":[283],"objectives":[286],"further":[291],"these":[293],"subgroups.":[298],"extensively":[301],"review":[302],"literature":[306],"support":[308],"taxonomy,":[310],"classifying":[311],"them":[312],"each":[314],"categories":[317],"propose.":[319]},"counts_by_year":[],"updated_date":"2026-04-05T06:14:27.290980","created_date":"2026-04-02T00:00:00"}