{"id":"https://openalex.org/W4412888858","doi":"https://doi.org/10.18653/v1/2025.findings-acl.100","title":"SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage","display_name":"SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888858","doi":"https://doi.org/10.18653/v1/2025.findings-acl.100"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.100","pdf_url":"https://aclanthology.org/2025.findings-acl.100.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.100.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003804285","display_name":"Xiaoning Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoning Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011995971","display_name":"Wenbo Hu","orcid":"https://orcid.org/0000-0002-8482-9400"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenbo Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105287777","display_name":"W. L. Xu","orcid":"https://orcid.org/0000-0002-6499-9103"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051747323","display_name":"Tianxing He","orcid":"https://orcid.org/0009-0008-6383-0307"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianxing He","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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1952","last_page":"1987"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12034","display_name":"Digital and Cyber Forensics","score":0.9922000169754028,"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"}},"topics":[{"id":"https://openalex.org/T12034","display_name":"Digital and Cyber Forensics","score":0.9922000169754028,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9661999940872192,"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/T11719","display_name":"Data Quality and Management","score":0.9386000037193298,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.6928354501724243},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.687401533126831},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6748478412628174},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.666787326335907},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5066531300544739},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16801553964614868},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12170693278312683},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09004774689674377},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.07160994410514832}],"concepts":[{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.6928354501724243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.687401533126831},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6748478412628174},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.666787326335907},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5066531300544739},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16801553964614868},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12170693278312683},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09004774689674377},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.07160994410514832},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.100","pdf_url":"https://aclanthology.org/2025.findings-acl.100.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.100","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.100","pdf_url":"https://aclanthology.org/2025.findings-acl.100.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G366789873","display_name":null,"funder_award_id":"62176135","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7422017672","display_name":null,"funder_award_id":"U2268202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888858.pdf","grobid_xml":"https://content.openalex.org/works/W4412888858.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2382521049","https://openalex.org/W2390279801","https://openalex.org/W1585007175","https://openalex.org/W4391913857","https://openalex.org/W4282976635","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"Large":[0],"language":[1,109,159],"models":[2],"(LLMs)":[3],"have":[4],"made":[5],"significant":[6],"advancements":[7],"across":[8],"various":[9],"tasks,":[10],"but":[11],"their":[12],"safety":[13],"alignment":[14],"remains":[15],"a":[16,59,84,89,102,107,151],"major":[17],"concern.Exploring":[18],"jailbreak":[19,61],"prompts":[20],"can":[21,69],"expose":[22],"LLMs'":[23],"vulnerabilities":[24],"and":[25,51,74,147,174,180,196],"guide":[26],"efforts":[27],"to":[28,39,87,135],"secure":[29],"them.Existing":[30],"methods":[31],"primarily":[32],"design":[33],"sophisticated":[34],"instructions":[35],"for":[36],"the":[37,49,120,123,128,132,138],"LLM":[38,72],"follow,":[40],"or":[41,95,112],"rely":[42],"on":[43,154],"multiple":[44,96],"iterations,":[45],"which":[46,68],"could":[47],"hinder":[48],"performance":[50,146],"efficiency":[52],"of":[53,122,172,178,194,198],"jailbreaks.In":[54],"this":[55],"work,":[56],"we":[57],"propose":[58],"novel":[60],"paradigm,":[62],"Simple":[63],"Assistive":[64],"Task":[65],"Linkage":[66],"(SATA),":[67],"effectively":[70],"circumvent":[71],"safeguards":[73],"elicit":[75],"harmful":[76,81,175],"responses.Specifically,":[77],"SATA":[78,126,143,164,189],"first":[79],"masks":[80],"keywords":[82],"within":[83],"malicious":[85],"query":[86,92,134],"generate":[88],"relatively":[90],"benign":[91],"containing":[93],"one":[94],"[MASK]":[97],"special":[98],"tokens.It":[99],"then":[100],"employs":[101],"simple":[103],"assistive":[104,129,162,187],"task-such":[105],"as":[106],"masked":[108,124,133],"model":[110,160],"task":[111,130],"an":[113,166,191],"element":[114,182],"lookup":[115,183],"by":[116,150,184],"position":[117,185],"task-to":[118],"encode":[119],"semantics":[121],"keywords.Finally,":[125],"links":[127],"with":[131,157,181],"jointly":[136],"perform":[137],"jailbreak.Extensive":[139],"experiments":[140],"show":[141],"that":[142],"achieves":[144,165],"state-ofthe-art":[145],"outperforms":[148],"baselines":[149],"large":[152],"margin.Specifically,":[153],"AdvBench":[155],"dataset,":[156],"mask":[158],"(MLM)":[161],"task,":[163,188],"overall":[167,192],"attack":[168],"success":[169],"rate":[170],"(ASR)":[171],"85%":[173],"score":[176],"(HS)":[177],"4.57,":[179],"(ELP)":[186],"attains":[190],"ASR":[193],"76%":[195],"HS":[197],"4.43":[199],"1":[200],".Warning:":[201],"This":[202],"work":[203],"contains":[204],"potentially":[205],"offensive":[206],"LLMs-generated":[207],"content.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
