{"id":"https://openalex.org/W4413277490","doi":"https://doi.org/10.1109/jiot.2025.3599199","title":"Fast and Controllable Bias-Guided Jailbreak Attack on Large Language Models","display_name":"Fast and Controllable Bias-Guided Jailbreak Attack on Large Language Models","publication_year":2025,"publication_date":"2025-08-18","ids":{"openalex":"https://openalex.org/W4413277490","doi":"https://doi.org/10.1109/jiot.2025.3599199"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2025.3599199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3599199","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-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/A5075336277","display_name":"Zi Kang","orcid":"https://orcid.org/0000-0002-1863-2802"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zi Kang","raw_affiliation_strings":["College of Computer Science and Technology, Ocean University of China, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080791772","display_name":"Hui Xia","orcid":"https://orcid.org/0000-0001-7326-5796"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Xia","raw_affiliation_strings":["College of Computer Science and Technology, Ocean University of China, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422044","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0002-4117-2656"},"institutions":[{"id":"https://openalex.org/I202126657","display_name":"Qufu Normal University","ror":"https://ror.org/03ceheh96","country_code":"CN","type":"education","lineage":["https://openalex.org/I202126657"]},{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["School of Cybersecurity, Qufu Normal University, Jining, China","College of Computer Science and Technology, Ocean University of China, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"School of Cybersecurity, Qufu Normal University, Jining, China","institution_ids":["https://openalex.org/I202126657"]},{"raw_affiliation_string":"College of Computer Science and Technology, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100957649","display_name":"Xiaoxue Song","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxue Song","raw_affiliation_strings":["College of Computer Science and Technology, Ocean University of China, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087321487","display_name":"Le Li","orcid":"https://orcid.org/0000-0001-5550-2997"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Li","raw_affiliation_strings":["College of Computer Science and Technology, Ocean University of China, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007408033","display_name":"Chunqiang Hu","orcid":"https://orcid.org/0000-0001-5825-2241"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunqiang Hu","raw_affiliation_strings":["School of Big Data and Software Engineering, Chongqing University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of Big Data and Software Engineering, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5075336277"],"corresponding_institution_ids":["https://openalex.org/I59028903"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11499182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"24","first_page":"51892","last_page":"51901"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.987500011920929,"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":0.987500011920929,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9749000072479248,"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/T10028","display_name":"Topic Modeling","score":0.9178000092506409,"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":0.7545663118362427},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3648262023925781}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7545663118362427},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3648262023925781}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2025.3599199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2025.3599199","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G5342570409","display_name":null,"funder_award_id":"62172377","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6320576782","display_name":null,"funder_award_id":"2024YFB3311802","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2896457183","https://openalex.org/W4367047229","https://openalex.org/W4378195097","https://openalex.org/W4385572096","https://openalex.org/W4388886073","https://openalex.org/W4393565548","https://openalex.org/W4402671039","https://openalex.org/W4402672077","https://openalex.org/W4403722520","https://openalex.org/W4404782326","https://openalex.org/W4405181600","https://openalex.org/W4405631861"],"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":[1,8],"models":[2],"(LLMs),":[3],"with":[4],"their":[5],"powerful":[6],"natural":[7],"processing":[9],"capabilities,":[10],"can":[11,32,145],"provide":[12],"more":[13],"advanced":[14],"intelligent":[15],"services":[16],"for":[17],"edge":[18,25],"devices.":[19],"However,":[20],"deploying":[21],"LLMs":[22],"at":[23],"the":[24,34,74,77,83,93,99,105,108,123,126,130,158],"is":[26],"vulnerable":[27],"to":[28,36,68,81,103,121,157,170,182],"jailbreak":[29,42,51,88,110,133,149],"attacks,":[30],"which":[31],"cause":[33],"model":[35,84],"generate":[37,146],"unsafe":[38],"content.":[39],"Meanwhile,":[40],"current":[41,159],"attack":[43,70,162,175],"schemes":[44],"are":[45],"inefficient":[46],"in":[47,85,174],"generating":[48,86],"highly":[49,147],"stealthy":[50,148],"prompts.":[52],"To":[53],"address":[54],"this,":[55],"we":[56,72,112],"propose":[57],"a":[58,152,171],"Fast":[59],"and":[60,117,184],"Controllable":[61],"Bias-Guided":[62],"Jailbreak":[63],"Attack":[64],"(FCB)":[65],"scheme.":[66],"First,":[67],"improve":[69],"efficiency,":[71],"optimize":[73],"bias":[75,118],"of":[76,107,132],"model\u2019s":[78],"output":[79,94],"layer":[80],"guide":[82],"low-energy":[87],"prompts":[89,134,150],"by":[90,180,188],"directly":[91],"adjusting":[92],"layer\u2019s":[95],"logits,":[96],"thereby":[97],"accelerating":[98],"decoding":[100],"process.":[101],"Second,":[102],"enhance":[104],"stealthiness":[106],"generated":[109],"prompts,":[111],"design":[113],"token":[114],"stop":[115],"selection":[116],"normalization":[119],"methods":[120],"constrain":[122],"perturbations":[124],"during":[125],"iterative":[127],"process,":[128],"preventing":[129],"generation":[131,163,186],"without":[135],"meaningful":[136],"semantics.":[137],"Finally,":[138],"extensive":[139],"experimental":[140],"results":[141],"demonstrate":[142],"that":[143],"FCB":[144,167],"within":[151],"short":[153],"time.":[154],"Specifically,":[155],"compared":[156],"state-of-the-art":[160],"controllable":[161],"scheme,":[164],"COLD":[165],"Attack,":[166],"achieves":[168],"up":[169,181],"8%":[172],"improvement":[173],"success":[176],"rate,":[177],"reduces":[178],"perplexity":[179],"181.171,":[183],"shortens":[185],"time":[187],"as":[189,191],"much":[190],"28":[192],"seconds.":[193]},"counts_by_year":[],"updated_date":"2025-12-11T23:09:37.256380","created_date":"2025-10-10T00:00:00"}