{"id":"https://openalex.org/W4404346764","doi":"https://doi.org/10.48550/arxiv.2410.23558","title":"Transferable & Stealthy Ensemble Attacks: A Black-Box Jailbreaking Framework for Large Language Models","display_name":"Transferable & Stealthy Ensemble Attacks: A Black-Box Jailbreaking Framework for Large Language Models","publication_year":2024,"publication_date":"2024-10-31","ids":{"openalex":"https://openalex.org/W4404346764","doi":"https://doi.org/10.48550/arxiv.2410.23558"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.23558","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.23558","pdf_url":"https://arxiv.org/pdf/2410.23558","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.23558","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yang, Yiqi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yiqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5114635459","display_name":"Hongye Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Hongye","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":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":0.9843000173568726,"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":0.9843000173568726,"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":0.9164000153541565,"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/black-box","display_name":"Black box","score":0.669769287109375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5454935431480408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2123253345489502}],"concepts":[{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.669769287109375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5454935431480408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2123253345489502}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.23558","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.23558","pdf_url":"https://arxiv.org/pdf/2410.23558","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.23558","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.23558","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.23558","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.23558","pdf_url":"https://arxiv.org/pdf/2410.23558","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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":{"We":[0],"present":[1],"a":[2],"novel":[3],"black-box":[4],"jailbreaking":[5,29,47],"framework":[6,20],"that":[7],"integrates":[8],"multiple":[9],"LLM-as-Attacker":[10],"strategies":[11],"to":[12,63],"deliver":[13],"highly":[14],"transferable":[15],"and":[16,31,52,73],"effective":[17],"attacks.":[18],"The":[19],"is":[21],"grounded":[22],"in":[23,38,46,68,82],"three":[24],"key":[25],"insights":[26],"from":[27],"prior":[28],"research":[30],"practice:":[32],"ensemble":[33],"approaches":[34],"outperform":[35],"single":[36],"methods":[37],"exposing":[39],"aligned":[40],"LLM":[41,72],"vulnerabilities,":[42],"malicious":[43,57],"instructions":[44],"vary":[45],"difficulty":[48],"requiring":[49],"tailored":[50],"optimization,":[51],"disrupting":[53],"semantic":[54],"coherence":[55],"of":[56],"prompts":[58],"can":[59],"manipulate":[60],"their":[61],"embeddings":[62],"boost":[64],"success":[65],"rates.":[66],"Validated":[67],"the":[69,83],"Competition":[70],"for":[71],"Agent":[74],"Safety":[75],"2024,":[76],"our":[77],"solution":[78],"achieved":[79],"top":[80],"rankings":[81],"Jailbreaking":[84],"Attack":[85],"Track.":[86]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}