{"id":"https://openalex.org/W7221004618","doi":"https://doi.org/10.48550/arxiv.2610.09167","title":"Detecting Unseen Jailbreak Sources: A Multi-Source Conformal Detection Perspective","display_name":"Detecting Unseen Jailbreak Sources: A Multi-Source Conformal Detection Perspective","publication_year":2026,"publication_date":"2026-10-06","ids":{"openalex":"https://openalex.org/W7221004618","doi":"https://doi.org/10.48550/arxiv.2610.09167"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.09167","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09167","pdf_url":"https://arxiv.org/pdf/2610.09167","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.09167","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135199411","display_name":"Xunlei Qian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qian, Xunlei","raw_affiliation_strings":["Department of Statistics and Probability , Michigan State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Probability , Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157902480","display_name":"Yingqian Cui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cui, Yingqian","raw_affiliation_strings":["Department of Computer Science and Engineering , Michigan State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157983966","display_name":"Yuping Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin, Yuping","raw_affiliation_strings":["Department of Computer Science and Engineering , Michigan State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157889228","display_name":"Jun Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu, Jun","raw_affiliation_strings":["Department of Computer Science and Engineering , Michigan State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041044132","display_name":"Yue Xing","orcid":"https://orcid.org/0000-0001-7723-0048","observed_orcids":["https://orcid.org/0000-0001-7723-0048"]},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xing, Yue","raw_affiliation_strings":["Department of Statistics and Probability , Michigan State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Probability , Michigan State University","institution_ids":["https://openalex.org/I87216513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87216513"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9951000213623047,"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":0.9951000213623047,"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/T11424","display_name":"Security and Verification in Computing","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/jailbreak-detection","display_name":"jailbreak detection","score":0.8790000081062317},{"id":"https://openalex.org/keywords/conformal-prediction","display_name":"conformal prediction","score":0.7049999833106995},{"id":"https://openalex.org/keywords/sequential-hypothesis-testing","display_name":"sequential hypothesis testing","score":0.8019999861717224},{"id":"https://openalex.org/keywords/large-language-model-security","display_name":"large language model security","score":0.6439999938011169},{"id":"https://openalex.org/keywords/adversarial-prompts","display_name":"adversarial prompts","score":0.5649999976158142},{"id":"https://openalex.org/keywords/probability-of-false-alarm","display_name":"false alarm probability","score":0.6589999794960022},{"id":"https://openalex.org/keywords/detection-power","display_name":"detection power","score":0.8360000252723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6133999824523926},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5453000068664551},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4902999997138977},{"id":"https://openalex.org/C141141315","wikidata":"https://www.wikidata.org/wiki/Q2379942","display_name":"Guard (computer science)","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.4796000123023987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44510000944137573},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4174000024795532},{"id":"https://openalex.org/C98214594","wikidata":"https://www.wikidata.org/wiki/Q850275","display_name":"Conformal map","level":2,"score":0.40540000796318054},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.35339999198913574},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3314000070095062},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C203763787","wikidata":"https://www.wikidata.org/wiki/Q371029","display_name":"Null (SQL)","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2768000066280365},{"id":"https://openalex.org/C191988596","wikidata":"https://www.wikidata.org/wiki/Q628374","display_name":"Null hypothesis","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26420000195503235},{"id":"https://openalex.org/C2778701210","wikidata":"https://www.wikidata.org/wiki/Q28130034","display_name":"Constructive","level":3,"score":0.25929999351501465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.09167","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09167","pdf_url":"https://arxiv.org/pdf/2610.09167","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2610.09167","doi":"https://doi.org/10.48550/arxiv.2610.09167","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.09167","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.09167","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09167","pdf_url":"https://arxiv.org/pdf/2610.09167","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221004618.pdf","grobid_xml":"https://content.openalex.org/works/W7221004618.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W3177813494","https://openalex.org/W4304195432","https://openalex.org/W4385374425","https://openalex.org/W4387559087","https://openalex.org/W4389226123","https://openalex.org/W4391463145","https://openalex.org/W4391555784","https://openalex.org/W4391632220","https://openalex.org/W4403885313","https://openalex.org/W4404570565","https://openalex.org/W4404783313","https://openalex.org/W4407212952","https://openalex.org/W4415248419","https://openalex.org/W4417095978","https://openalex.org/W4417299992","https://openalex.org/W4417353149","https://openalex.org/W7118698363","https://openalex.org/W7163867469","https://openalex.org/W7171934915"],"related_works":["https://openalex.org/W7163867469","https://openalex.org/W4411552743","https://openalex.org/W4417113114","https://openalex.org/W7105648983","https://openalex.org/W7130601313","https://openalex.org/W7117551250","https://openalex.org/W4412945189","https://openalex.org/W4416549802","https://openalex.org/W7115176063","https://openalex.org/W6929204117"],"abstract_inverted_index":{"Jailbreak":[0],"defenses":[1],"for":[2],"large":[3],"language":[4],"models":[5],"are":[6,28,171],"usually":[7],"calibrated":[8],"on":[9,182],"a":[10,47,68,88,132,138,162,204],"fixed":[11],"set":[12],"of":[13,49,81,128,141,184],"known":[14,62,83,93,105,176],"attack":[15,19,50,58],"methods.":[16],"However,":[17],"new":[18,34],"methods":[20],"keep":[21],"appearing":[22],"after":[23],"deployment,":[24],"and":[25,95,116,122,160,194,202],"existing":[26],"detectors":[27],"observed":[29],"to":[30,44,166],"degrade":[31],"under":[32],"the":[33,53,61,76,82,97,101,157],"attacks":[35],"(Piet":[36],"et":[37,191,199],"al.,":[38,192,200],"2025).":[39],"This":[40],"paper":[41],"studies":[42],"how":[43],"detect,":[45],"from":[46,56,79,174],"stream":[48,77],"prompts,":[51],"that":[52,75,135,148,170],"prompts":[54],"come":[55],"an":[57],"source":[59,106],"outside":[60],"ones.":[63],"We":[64],"formulate":[65],"it":[66],"as":[67,156],"sequential":[69],"test":[70],"whose":[71],"null":[72,98],"hypothesis":[73],"is":[74,107],"comes":[78],"one":[80,153],"sources.":[84,177],"Methodology-wise,":[85],"we":[86,113,179],"compute":[87],"conformal":[89],"p-value":[90],"against":[91,103],"each":[92],"source,":[94],"reject":[96],"only":[99,137],"when":[100],"evidence":[102],"every":[104],"large.":[108],"Using":[109],"these":[110],"source-wise":[111],"p-values,":[112],"build":[114],"Persist-3":[115,129,181],"analyze":[117],"its":[118,149],"stationary":[119],"false-alarm":[120],"probability":[121,151],"detection":[123,133,150],"power.":[124],"The":[125],"technical":[126],"contribution":[127],"lies":[130],"in":[131],"guarantee":[134],"uses":[136],"finite":[139],"window":[140,158,164],"recent":[142,186],"observations.":[143],"Our":[144],"theoretical":[145],"analysis":[146],"reveals":[147],"approaches":[152],"exponentially":[154],"fast":[155],"grows,":[159],"thus":[161],"short":[163],"suffices":[165],"detect":[167],"unseen":[168],"sources":[169],"well":[172],"separated":[173],"all":[175],"Empirically,":[178],"validate":[180],"top":[183],"two":[185],"jailbreak":[187],"defenses,":[188],"MTK":[189],"(Zhang":[190],"2026)":[193],"Prompt":[195],"Guard":[196],"2":[197],"(Chennabasappa":[198],"2025),":[201],"observe":[203],"significant":[205],"defense":[206],"enhancement.":[207]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-09T00:00:00"}