{"id":"https://openalex.org/W4406457838","doi":"https://doi.org/10.1109/bigdata62323.2024.10825267","title":"AutoRed: Automated Attack Scenario Generation Framework for Red Teaming of LLMs","display_name":"AutoRed: Automated Attack Scenario Generation Framework for Red Teaming of LLMs","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406457838","doi":"https://doi.org/10.1109/bigdata62323.2024.10825267"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825267","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/A5100407591","display_name":"Zhe Wang","orcid":"https://orcid.org/0000-0001-9727-5569"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Zhe Wang","raw_affiliation_strings":["Simon Fraser University,School of Computing Science,Burnaby,Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University,School of Computing Science,Burnaby,Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060953615","display_name":"Mohammad A. Tayebi","orcid":"https://orcid.org/0009-0006-8689-9038"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mohammad A. Tayebi","raw_affiliation_strings":["Simon Fraser University,School of Computing Science,Burnaby,Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University,School of Computing Science,Burnaby,Canada","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100407591"],"corresponding_institution_ids":["https://openalex.org/I18014758"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2807603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2376","last_page":"2383"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9846000075340271,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9739999771118164,"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":0.6233471035957336},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3929135799407959}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6233471035957336},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3929135799407959}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825267","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W2963329071","https://openalex.org/W3027879771","https://openalex.org/W3105922288","https://openalex.org/W4226278401","https://openalex.org/W4286987939","https://openalex.org/W4288089799","https://openalex.org/W4302305863","https://openalex.org/W4304195432","https://openalex.org/W4361866125","https://openalex.org/W4378771755","https://openalex.org/W4382998379","https://openalex.org/W4385245566","https://openalex.org/W4385894687","https://openalex.org/W4387294543","https://openalex.org/W4387596201","https://openalex.org/W4387838992","https://openalex.org/W4388092128","https://openalex.org/W4388329043","https://openalex.org/W4388886073","https://openalex.org/W4389519928","https://openalex.org/W6741002519","https://openalex.org/W6763393573","https://openalex.org/W6765947440","https://openalex.org/W6769627184","https://openalex.org/W6777615688","https://openalex.org/W6787335730","https://openalex.org/W6800875267","https://openalex.org/W6810738896","https://openalex.org/W6846095518","https://openalex.org/W6846254642","https://openalex.org/W6850820320","https://openalex.org/W6852418670","https://openalex.org/W6857146736","https://openalex.org/W6857318322","https://openalex.org/W6857711932","https://openalex.org/W6858129433","https://openalex.org/W6922480057"],"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":{"Even":[0],"though":[1],"Large":[2],"Language":[3],"Models":[4],"(LLMs)":[5],"are":[6],"highly":[7],"beneficial,":[8],"they":[9],"pose":[10],"significant":[11],"security":[12,206],"concerns,":[13],"particularly":[14],"in":[15],"the":[16,39,46,164,174,182,189],"realm":[17],"of":[18,41,111,166,176,185,191],"privacy":[19],"protection.":[20],"Sensitive":[21],"information":[22,99,134],"is":[23,55,76],"often":[24],"provided":[25],"to":[26,64,90,115,121,144],"LLMs":[27,120],"during":[28],"conversations":[29],"and":[30,79,136,160,204],"may":[31],"be":[32],"retained":[33],"as":[34,195],"in-context":[35],"memory.":[36],"This":[37,81,168],"raises":[38],"risk":[40],"unintended":[42],"data":[43],"exposure.":[44],"In":[45],"existing":[47],"paradigm,":[48],"a":[49,149],"red":[50,198],"team":[51],"comprising":[52],"human":[53,74],"testers":[54,75],"tasked":[56],"with":[57],"generating":[58],"input":[59],"prompts":[60,114],"(i.e.,":[61],"test":[62],"cases)":[63],"provoke":[65],"undesirable":[66],"responses":[67],"from":[68,100,119],"LLMs.":[69,101,208],"Yet,":[70],"relying":[71],"solely":[72],"on":[73,107],"both":[77],"costly":[78],"time-intensive.":[80],"paper":[82],"presents":[83],"AutoRed,":[84],"an":[85,196],"innovative":[86],"learning":[87],"framework":[88,103,194],"developed":[89],"automatically":[91],"generate":[92],"malicious":[93,113,130],"attack":[94],"scenarios":[95],"for":[96,201],"extracting":[97],"sensitive":[98,133],"Our":[102,152],"places":[104],"particular":[105],"emphasis":[106],"prompt":[108,131,146],"injection\u2014the":[109],"process":[110],"injecting":[112],"extract":[116],"conversation":[117],"histories":[118],"uncover":[122],"private":[123],"data.":[124],"AutoRed":[125],"comprises":[126],"three":[127],"key":[128],"components:":[129],"generator,":[132],"extractor,":[135],"stop":[137],"point":[138],"identifier.":[139],"These":[140],"components":[141],"work":[142],"together":[143],"enable":[145],"injection,":[147],"ensuring":[148],"seamless":[150],"process.":[151],"extensive":[153],"experimental":[154],"evaluation,":[155],"spanning":[156],"diverse":[157],"defense":[158,177],"strategies":[159],"various":[161],"LLMs,":[162,186],"demonstrates":[163],"efficacy":[165],"AutoRed.":[167],"evaluation":[169],"not":[170],"only":[171],"rigorously":[172],"assesses":[173],"resilience":[175],"mechanisms":[178],"but":[179],"also":[180],"measures":[181],"safety":[183],"alignment":[184],"thereby":[187],"highlighting":[188],"potential":[190],"our":[192],"automated":[193],"efficient":[197],"teaming":[199],"tool":[200],"identifying":[202],"vulnerabilities":[203],"enhancing":[205],"within":[207]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}