{"id":"https://openalex.org/W7129300093","doi":"https://doi.org/10.1109/tai.2026.3665656","title":"Prompt-Based Jailbreaking of Leading LLM Chatbots: A Survey of Attacks and Defenses","display_name":"Prompt-Based Jailbreaking of Leading LLM Chatbots: A Survey of Attacks and Defenses","publication_year":2026,"publication_date":"2026-02-17","ids":{"openalex":"https://openalex.org/W7129300093","doi":"https://doi.org/10.1109/tai.2026.3665656"},"language":null,"primary_location":{"id":"doi:10.1109/tai.2026.3665656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2026.3665656","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-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/A5126222427","display_name":"Brynn Knowlton","orcid":null},"institutions":[{"id":"https://openalex.org/I43369023","display_name":"California State University, San Bernardino","ror":"https://ror.org/02n651896","country_code":"US","type":"education","lineage":["https://openalex.org/I43369023"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brynn Knowlton","raw_affiliation_strings":["California State University San Bernardino (CSUSB) San Bernardino"],"raw_orcid":"https://orcid.org/0009-0006-8623-6592","affiliations":[{"raw_affiliation_string":"California State University San Bernardino (CSUSB) San Bernardino","institution_ids":["https://openalex.org/I43369023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126190492","display_name":"Jovani Campa","orcid":null},"institutions":[{"id":"https://openalex.org/I43369023","display_name":"California State University, San Bernardino","ror":"https://ror.org/02n651896","country_code":"US","type":"education","lineage":["https://openalex.org/I43369023"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jovani Campa","raw_affiliation_strings":["California State University San Bernardino (CSUSB) San Bernardino"],"raw_orcid":"https://orcid.org/0009-0002-5227-5885","affiliations":[{"raw_affiliation_string":"California State University San Bernardino (CSUSB) San Bernardino","institution_ids":["https://openalex.org/I43369023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126258118","display_name":"David Solis Gallo","orcid":null},"institutions":[{"id":"https://openalex.org/I43369023","display_name":"California State University, San Bernardino","ror":"https://ror.org/02n651896","country_code":"US","type":"education","lineage":["https://openalex.org/I43369023"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Solis Gallo","raw_affiliation_strings":["California State University San Bernardino (CSUSB) San Bernardino"],"raw_orcid":"https://orcid.org/0009-0004-0914-6927","affiliations":[{"raw_affiliation_string":"California State University San Bernardino (CSUSB) San Bernardino","institution_ids":["https://openalex.org/I43369023"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076375195","display_name":"Khalil Dajani","orcid":null},"institutions":[{"id":"https://openalex.org/I43369023","display_name":"California State University, San Bernardino","ror":"https://ror.org/02n651896","country_code":"US","type":"education","lineage":["https://openalex.org/I43369023"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khalil Dajani","raw_affiliation_strings":["California State University San Bernardino (CSUSB) San Bernardino"],"raw_orcid":"https://orcid.org/0000-0003-1061-4236","affiliations":[{"raw_affiliation_string":"California State University San Bernardino (CSUSB) San Bernardino","institution_ids":["https://openalex.org/I43369023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070375370","display_name":"Nabeel Alzahrani","orcid":"https://orcid.org/0009-0008-5671-7277"},"institutions":[{"id":"https://openalex.org/I43369023","display_name":"California State University, San Bernardino","ror":"https://ror.org/02n651896","country_code":"US","type":"education","lineage":["https://openalex.org/I43369023"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nabeel Alzahrani","raw_affiliation_strings":["California State University San Bernardino (CSUSB) San Bernardino"],"raw_orcid":"https://orcid.org/0009-0008-5671-7277","affiliations":[{"raw_affiliation_string":"California State University San Bernardino (CSUSB) San Bernardino","institution_ids":["https://openalex.org/I43369023"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I43369023"],"apc_list":null,"apc_paid":null,"fwci":21.8879,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.99140889,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"7","issue":"8","first_page":"4237","last_page":"4251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.795799970626831,"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":0.795799970626831,"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/T10028","display_name":"Topic Modeling","score":0.03779999911785126,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.024299999698996544,"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":0.8147000074386597},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6413999795913696},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5335000157356262},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48750001192092896},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.35830000042915344},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.34119999408721924}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8147000074386597},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6413999795913696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5841000080108643},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5335000157356262},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5192000269889832},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48750001192092896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4221000075340271},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C2987082051","wikidata":"https://www.wikidata.org/wiki/Q223642","display_name":"Human interaction","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3093000054359436},{"id":"https://openalex.org/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C2778440437","wikidata":"https://www.wikidata.org/wiki/Q2336124","display_name":"Defamiliarization","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29750001430511475},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29600000381469727},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C117035363","wikidata":"https://www.wikidata.org/wiki/Q3769299","display_name":"Human behavior","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tai.2026.3665656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2026.3665656","pdf_url":null,"source":{"id":"https://openalex.org/S4210169448","display_name":"IEEE Transactions on Artificial Intelligence","issn_l":"2691-4581","issn":["2691-4581"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.48954087495803833,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W4389736946","https://openalex.org/W4391724817","https://openalex.org/W4392904091","https://openalex.org/W4395034112","https://openalex.org/W4396917902","https://openalex.org/W4401042173","https://openalex.org/W4401042350","https://openalex.org/W4401042853","https://openalex.org/W4402669751","https://openalex.org/W4402670855","https://openalex.org/W4402671039","https://openalex.org/W4402671718","https://openalex.org/W4402671828","https://openalex.org/W4404515027","https://openalex.org/W4404518370","https://openalex.org/W4404612289","https://openalex.org/W4404740556","https://openalex.org/W4404781557","https://openalex.org/W4405181744","https://openalex.org/W4406028197","https://openalex.org/W4406457934","https://openalex.org/W4406458169","https://openalex.org/W4406460462","https://openalex.org/W4407506574","https://openalex.org/W4408146479","https://openalex.org/W4408863199","https://openalex.org/W4409657133","https://openalex.org/W4409657529","https://openalex.org/W4409735455","https://openalex.org/W4411113102","https://openalex.org/W4412886812","https://openalex.org/W4412888372","https://openalex.org/W4413146423","https://openalex.org/W4415797457","https://openalex.org/W4415797606","https://openalex.org/W4415797762","https://openalex.org/W4415798173","https://openalex.org/W4416036027","https://openalex.org/W4416549384","https://openalex.org/W6941158388","https://openalex.org/W7133204634"],"related_works":[],"abstract_inverted_index":{"Generative":[0],"AI":[1],"systems\u2014particularly":[2],"large":[3],"language":[4],"models":[5],"(LLMs)\u2014remain":[6],"vulnerable":[7],"to":[8],"jailbreak":[9,25,143],"attacks:":[10],"adversarial":[11,89],"prompts":[12],"that":[13],"bypass":[14],"safeguards":[15],"and":[16,34,55,68,75,91,101,111,119,129,145],"elicit":[17],"unsafe":[18],"or":[19,52,93],"restricted":[20],"outputs.":[21],"This":[22,132],"survey":[23],"synthesizes":[24],"research":[26],"from":[27,85],"2023\u20132025,":[28],"covering":[29],"attack":[30],"methods,":[31],"defense":[32,77],"strategies,":[33],"evaluation":[35,103],"frameworks.":[36],"Jailbreak":[37],"techniques":[38],"are":[39,121],"grouped":[40],"into":[41],"five":[42],"main":[43],"categories:":[44],"prompt-based":[45],"injections,":[46],"role-play":[47],"conditioning,":[48],"multi-turn":[49],"dialogue,":[50],"multilingual":[51],"multimodal":[53,102],"exploits,":[54],"optimization-driven":[56],"pipelines.":[57],"We":[58],"also":[59],"examine":[60],"discovery":[61],"methods":[62],"such":[63],"as":[64,98],"human":[65,86],"red":[66],"teaming":[67],"automated":[69],"attacker":[70],"systems":[71],"(e.g.,":[72],"AutoJailbreak,":[73],"LLMStinger),":[74],"review":[76],"mechanisms":[78],"including":[79],"supervised":[80],"fine-tuning":[81],"(SFT),":[82],"reinforcement":[83],"learning":[84],"feedback":[87],"(RLHF),":[88],"fine-tuning,":[90],"output":[92],"pipeline":[94],"filtering.":[95],"Standardized":[96],"benchmarks\u2014such":[97],"PromptBench,":[99],"JailbreakBench,":[100],"suites\u2014are":[104],"analyzed":[105],"in":[106,147],"terms":[107],"of":[108,116,142],"reproducibility,":[109,118],"coverage,":[110],"robustness":[112],"testing.":[113],"Persistent":[114],"issues":[115],"generalization,":[117],"scalability":[120],"discussed,":[122],"along":[123],"with":[124],"tradeoffs":[125],"between":[126],"safety":[127],"alignment":[128],"model":[130],"utility.":[131],"paper":[133],"provides":[134],"an":[135],"up-to-date":[136],"reference":[137],"clarifying":[138],"the":[139],"evolving":[140],"landscape":[141],"attacks":[144],"defenses":[146],"LLMs.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2026-02-18T00:00:00"}