{"id":"https://openalex.org/W4412876840","doi":"https://doi.org/10.1145/3711896.3737014","title":"Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models","display_name":"Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412876840","doi":"https://doi.org/10.1145/3711896.3737014"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737014","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737014","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737014","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737014","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070578353","display_name":"Shangqing Tu","orcid":"https://orcid.org/0009-0008-0640-3413"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangqing Tu","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-0640-3413","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101381935","display_name":"Zhuoran Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoran Pan","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-8141-5587","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106746626","display_name":"Wenxuan Wang","orcid":"https://orcid.org/0000-0002-9803-8204"},"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":"Wenxuan Wang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-9803-8204","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102245113","display_name":"Zhexin Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhexin Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-9601-3991","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuliang Sun","orcid":"https://orcid.org/0009-0003-8380-6041"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuliang Sun","raw_affiliation_strings":["CSE, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-8380-6041","affiliations":[{"raw_affiliation_string":"CSE, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038246814","display_name":"Jifan Yu","orcid":"https://orcid.org/0000-0003-3430-4048"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jifan Yu","raw_affiliation_strings":["IoE, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3430-4048","affiliations":[{"raw_affiliation_string":"IoE, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085094109","display_name":"Hongning Wang","orcid":"https://orcid.org/0000-0002-6524-9195"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongning Wang","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6524-9195","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060498828","display_name":"Lei Hou","orcid":"https://orcid.org/0000-0002-8907-3526"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Hou","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8907-3526","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003324011","display_name":"Juanzi Li","orcid":"https://orcid.org/0000-0002-6244-0664"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juanzi Li","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6244-0664","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"2847","last_page":"2858"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12034","display_name":"Digital and Cyber Forensics","score":0.9775999784469604,"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":0.9775999784469604,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9700000286102295,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9478999972343445,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7335051894187927},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4627736806869507},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.4230092167854309}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7335051894187927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4627736806869507},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.4230092167854309}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3737014","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737014","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737014","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711896.3737014","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3737014","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3737014","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.550000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412876840.pdf","grobid_xml":"https://content.openalex.org/works/W4412876840.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2115642684","https://openalex.org/W2343924243","https://openalex.org/W3099700870","https://openalex.org/W4389524209","https://openalex.org/W4405181600","https://openalex.org/W6600168703","https://openalex.org/W6602670149","https://openalex.org/W6820618299"],"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":{"Large":[0],"language":[1,95],"models":[2],"(LLMs)":[3],"have":[4],"been":[5],"increasingly":[6],"applied":[7],"to":[8,68,99,124,130,139,155],"various":[9],"domains,":[10,20],"which":[11,66],"triggers":[12],"increasing":[13],"concerns":[14],"about":[15],"LLMs'":[16],"safety":[17,42],"on":[18,26,38,105],"specialized":[19],"e.g.":[21],"medicine.":[22],"Despite":[23],"prior":[24],"explorations":[25],"general":[27],"jailbreaking":[28,70],"attacks,":[29],"there":[30],"are":[31,121,151,164],"two":[32],"challenges":[33],"for":[34],"applying":[35],"existing":[36],"attacks":[37,71],"testing":[39],"the":[40,113,125,131],"domain-specific":[41],"of":[43,47,53,115],"LLMs:":[44],"(1)":[45],"Lack":[46],"professional":[48],"knowledge-driven":[49],"attacks(2)":[50],"Insufficient":[51],"coverage":[52],"domain":[54,73,101],"knowledge.":[55,133],"To":[56],"bridge":[57],"this":[58],"gap,":[59],"we":[60],"propose":[61],"a":[62,84,93],"new":[63],"task,":[64],"knowledge-to-jailbreak,":[65],"aims":[67],"generate":[69,148],"from":[72],"knowledge,":[74],"requiring":[75],"both":[76,122],"attack":[77],"effectiveness":[78,114],"and":[79,91,108,128,162],"knowledge":[80,142],"relevance.":[81],"We":[82,134],"collect":[83],"large-scale":[85],"dataset":[86],"with":[87],"12,974":[88],"knowledge-jailbreak":[89],"pairs":[90],"fine-tune":[92],"large":[94],"model":[96],"as":[97],"jailbreak-generator,":[98],"produce":[100],"knowledge-specific":[102],"jailbreaks.":[103],"Experiments":[104],"13":[106],"domains":[107],"8":[109],"target":[110,126],"LLMs":[111,127],"demonstrate":[112],"jailbreak-generator":[116,146],"in":[117,153],"generating":[118],"jailbreaks":[119,149],"that":[120,145,150],"threatening":[123],"relevant":[129],"given":[132],"also":[135],"apply":[136],"our":[137],"method":[138],"an":[140],"out-of-domain":[141],"base,":[143],"showing":[144],"can":[147],"comparable":[152],"harmfulness":[154],"those":[156],"crafted":[157],"by":[158],"human":[159],"experts.":[160],"Data":[161],"code":[163],"available":[165],"at:":[166],"https://github.com/THU-KEG/Knowledge-to-Jailbreak/.":[167]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
