{"id":"https://openalex.org/W4409356470","doi":"https://doi.org/10.1109/tvcg.2025.3557568","title":"JailbreakHunter: A Visual Analytics Approach for Jailbreak Prompts Discovery From Large-Scale Human-LLM Conversational Datasets","display_name":"JailbreakHunter: A Visual Analytics Approach for Jailbreak Prompts Discovery From Large-Scale Human-LLM Conversational Datasets","publication_year":2025,"publication_date":"2025-04-11","ids":{"openalex":"https://openalex.org/W4409356470","doi":"https://doi.org/10.1109/tvcg.2025.3557568","pmid":"https://pubmed.ncbi.nlm.nih.gov/40215145"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2025.3557568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2025.3557568","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"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 Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5005458050","display_name":"Zhihua Jin","orcid":"https://orcid.org/0000-0001-7047-7988"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Zhihua Jin","raw_affiliation_strings":["Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong","Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065964824","display_name":"Shiyi Liu","orcid":"https://orcid.org/0009-0009-0174-0952"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiyi Liu","raw_affiliation_strings":["Arizona State University, Tempe, AZ, USA","Arizona State University"],"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397330","display_name":"Haotian Li","orcid":"https://orcid.org/0000-0001-9547-3449"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Haotian Li","raw_affiliation_strings":["Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong","Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063519388","display_name":"Xun Zhao","orcid":"https://orcid.org/0000-0002-1767-6520"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Zhao","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China","Shanghai AI Laboratory"],"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091466289","display_name":"Huamin Qu","orcid":"https://orcid.org/0000-0002-3344-9694"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Huamin Qu","raw_affiliation_strings":["Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong","Hong Kong University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005458050"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":8.0194,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.96159332,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"31","issue":"10","first_page":"7923","last_page":"7937"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10574","display_name":"Crime Patterns and Interventions","score":0.9853000044822693,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10574","display_name":"Crime Patterns and Interventions","score":0.9853000044822693,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/T12034","display_name":"Digital and Cyber Forensics","score":0.9758999943733215,"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/T13728","display_name":"Crime, Deviance, and Social Control","score":0.9375,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7913542985916138},{"id":"https://openalex.org/keywords/visual-analytics","display_name":"Visual analytics","score":0.6982448697090149},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.6288450956344604},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5656209588050842},{"id":"https://openalex.org/keywords/cultural-analytics","display_name":"Cultural analytics","score":0.5541488528251648},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.5503838658332825},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5251083970069885},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5086373090744019},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.48562780022621155},{"id":"https://openalex.org/keywords/interactive-visual-analysis","display_name":"Interactive visual analysis","score":0.41686248779296875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33454760909080505},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2922716736793518},{"id":"https://openalex.org/keywords/semantic-analytics","display_name":"Semantic analytics","score":0.18963581323623657},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.14001795649528503},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.08246633410453796}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7913542985916138},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.6982448697090149},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.6288450956344604},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5656209588050842},{"id":"https://openalex.org/C545860419","wikidata":"https://www.wikidata.org/wiki/Q5193251","display_name":"Cultural analytics","level":5,"score":0.5541488528251648},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.5503838658332825},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5251083970069885},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5086373090744019},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.48562780022621155},{"id":"https://openalex.org/C99740376","wikidata":"https://www.wikidata.org/wiki/Q17092520","display_name":"Interactive visual analysis","level":4,"score":0.41686248779296875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33454760909080505},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2922716736793518},{"id":"https://openalex.org/C148792806","wikidata":"https://www.wikidata.org/wiki/Q7449046","display_name":"Semantic analytics","level":4,"score":0.18963581323623657},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.14001795649528503},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.08246633410453796},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003142","descriptor_name":"Communication","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003142","descriptor_name":"Communication","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016494","descriptor_name":"Computer Security","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016494","descriptor_name":"Computer Security","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1109/tvcg.2025.3557568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2025.3557568","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"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 Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:40215145","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40215145","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":null},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-169000","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-169000","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2014268383","https://openalex.org/W2148893894","https://openalex.org/W2157821464","https://openalex.org/W2204875540","https://openalex.org/W2291242049","https://openalex.org/W2470422954","https://openalex.org/W2506550404","https://openalex.org/W2752194699","https://openalex.org/W2793981077","https://openalex.org/W2796420997","https://openalex.org/W2797751845","https://openalex.org/W2812765312","https://openalex.org/W2950784811","https://openalex.org/W2963123635","https://openalex.org/W2964200170","https://openalex.org/W2970641574","https://openalex.org/W2996005046","https://openalex.org/W3029037612","https://openalex.org/W3038035611","https://openalex.org/W3093452197","https://openalex.org/W3175487198","https://openalex.org/W3217249349","https://openalex.org/W4283269716","https://openalex.org/W4285210452","https://openalex.org/W4287888350","https://openalex.org/W4288761543","https://openalex.org/W4301393026","https://openalex.org/W4315778472","https://openalex.org/W4379929801","https://openalex.org/W4381572755","https://openalex.org/W4382318449","https://openalex.org/W4385571801","https://openalex.org/W4385679821","https://openalex.org/W4387425757","https://openalex.org/W4387966251","https://openalex.org/W4389518687","https://openalex.org/W4389518968","https://openalex.org/W4389519367","https://openalex.org/W4389523893","https://openalex.org/W4396833346","https://openalex.org/W4400315206","https://openalex.org/W4402672051","https://openalex.org/W4402684226","https://openalex.org/W4405181600","https://openalex.org/W4406152279","https://openalex.org/W4410609100"],"related_works":["https://openalex.org/W2148525144","https://openalex.org/W1813318416","https://openalex.org/W3173715284","https://openalex.org/W2564956852","https://openalex.org/W2158984754","https://openalex.org/W3149127250","https://openalex.org/W4246764483","https://openalex.org/W3208630418","https://openalex.org/W2112083262","https://openalex.org/W2166699593"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4,28,140],"gained":[5],"significant":[6],"attention":[7],"but":[8],"also":[9],"raised":[10],"concerns":[11],"due":[12,99],"to":[13,33,66,83,89,100,156,206],"the":[14,35,91,101,158,186,189,208,219,225,236],"risk":[15],"of":[16,23,38,77,104,109,160,188,191,227,235],"misuse.":[17],"Jailbreak":[18],"prompts,":[19,74,111,222],"a":[20,126,142,215],"popular":[21],"type":[22],"adversarial":[24],"attack":[25,180],"towards":[26],"LLMs,":[27],"appeared":[29],"and":[30,112,150,162,179,193,211,218,233,244],"constantly":[31],"evolved":[32],"breach":[34],"safety":[36,49],"protocols":[37],"LLMs.":[39,68],"To":[40,69,119],"address":[41],"this":[42],"issue,":[43],"LLMs":[44],"are":[45],"regularly":[46],"updated":[47],"with":[48,144,172],"patches":[50],"based":[51],"on":[52],"reported":[53,173,220],"jailbreak":[54,63,73,110,132,174,196,221,229],"prompts.":[55],"However,":[56],"malicious":[57],"users":[58,155,205],"often":[59],"keep":[60],"their":[61,113,199],"successful":[62],"prompts":[64,85,133,175,197],"private":[65,72],"exploit":[67],"uncover":[70],"these":[71,121],"extensive":[75],"analysis":[76,146,153,184,203],"large-scale":[78,135],"conversational":[79,137],"datasets":[80],"is":[81,96],"necessary":[82],"identify":[84,163],"that":[86],"still":[87],"manage":[88],"bypass":[90],"system's":[92],"defenses.":[93],"This":[94],"task":[95],"highly":[97],"challenging":[98],"immense":[102],"volume":[103],"conversation":[105,200],"data,":[106],"diverse":[107],"characteristics":[108],"presence":[114],"in":[115,134,176,224],"complex":[116],"multi-turn":[117],"conversations.":[118],"tackle":[120],"challenges,":[122],"we":[123],"introduce":[124],"JailbreakHunter,":[125],"visual":[127],"analytics":[128],"approach":[129],"for":[130],"identifying":[131],"human-LLM":[136],"datasets.":[138],"We":[139],"designed":[141],"workflow":[143],"three":[145],"levels:":[147],"group-level,":[148],"conversation-level,":[149],"turn-level.":[151],"Group-level":[152],"enables":[154],"grasp":[157],"distribution":[159],"conversations":[161,165,192],"suspicious":[164],"using":[166],"multiple":[167,241],"criteria,":[168],"such":[169],"as":[170],"similarity":[171,210],"previous":[177],"research":[178],"success":[181],"rates.":[182],"Conversation-level":[183],"facilitates":[185],"understanding":[187],"progress":[190],"helps":[194],"discover":[195],"within":[198],"contexts.":[201],"Turn-level":[202],"allows":[204],"explore":[207],"semantic":[209],"token":[212],"overlap":[213],"between":[214],"single-turn":[216],"prompt":[217],"aiding":[223],"identification":[226],"new":[228],"strategies.":[230],"The":[231],"effectiveness":[232],"usability":[234],"system":[237],"were":[238],"verified":[239],"through":[240],"case":[242],"studies":[243],"expert":[245],"interviews.":[246]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-04-12T00:00:00"}
