{"id":"https://openalex.org/W4404780985","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.803","title":"Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models","display_name":"Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404780985","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.803"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.findings-emnlp.803","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.803","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.803","pdf_url":"https://aclanthology.org/2024.findings-emnlp.803.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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: EMNLP 2024","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2024.findings-emnlp.803.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100378204","display_name":"Yue Xu","orcid":"https://orcid.org/0009-0000-0967-9062","observed_orcids":["https://orcid.org/0009-0000-0967-9062","https://orcid.org/0009-0004-7257-2216","https://orcid.org/0000-0003-2366-8807","https://orcid.org/0000-0001-7998-1769"]},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Xu","raw_affiliation_strings":["School of Information Science and Technology , ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology , ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042857471","display_name":"Xiuyuan Qi","orcid":"https://orcid.org/0009-0006-5377-7106","observed_orcids":["https://orcid.org/0009-0006-5377-7106"]},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuyuan Qi","raw_affiliation_strings":["School of Information Science and Technology , ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology , ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043524348","display_name":"Zhan Qin","orcid":"https://orcid.org/0000-0001-7872-6969","observed_orcids":["https://orcid.org/0000-0001-7872-6969"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Qin","raw_affiliation_strings":["The State Key Laboratory of Blockchain and Data Security , Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The State Key Laboratory of Blockchain and Data Security , Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044772153","display_name":"Wenjie Wang","orcid":"https://orcid.org/0000-0002-3103-8445","observed_orcids":["https://orcid.org/0000-0002-3103-8445"]},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Wang","raw_affiliation_strings":["School of Information Science and Technology , ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology , ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4969,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":{"value":0.96862487,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"13715","last_page":"13726"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994999766349792,"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":0.9994999766349792,"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/T12357","display_name":"Digital Media Forensic Detection","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9950000047683716},{"id":"https://openalex.org/keywords/cross-modal-similarity","display_name":"cross-modal similarity","score":0.8009999990463257},{"id":"https://openalex.org/keywords/model-transferability","display_name":"model transferability","score":0.6200000047683716},{"id":"https://openalex.org/keywords/cider","display_name":"cider","score":0.5419999957084656}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.768600583076477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7682514786720276},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5646944642066956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47925615310668945}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2024.findings-emnlp.803","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.803","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.803","pdf_url":"https://aclanthology.org/2024.findings-emnlp.803.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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: EMNLP 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2407.21659","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.21659","pdf_url":"https://arxiv.org/pdf/2407.21659","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.2407.21659","doi":"https://doi.org/10.48550/arxiv.2407.21659","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.21659","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-emnlp.803","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.803","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.803","pdf_url":"https://aclanthology.org/2024.findings-emnlp.803.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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: EMNLP 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322927","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404780985.pdf","grobid_xml":"https://content.openalex.org/works/W4404780985.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1945616565","https://openalex.org/W3094502228","https://openalex.org/W4327810158","https://openalex.org/W4362515116","https://openalex.org/W4366850747","https://openalex.org/W4384918448","https://openalex.org/W4385374425","https://openalex.org/W4385645323","https://openalex.org/W4386185600","https://openalex.org/W4388482181","https://openalex.org/W4391590851","https://openalex.org/W4391590954","https://openalex.org/W4391632220","https://openalex.org/W4394007075","https://openalex.org/W4402727490","https://openalex.org/W4403878024","https://openalex.org/W4404356490","https://openalex.org/W4404725774","https://openalex.org/W4404783010","https://openalex.org/W4404792953","https://openalex.org/W4404971291","https://openalex.org/W4408612358","https://openalex.org/W4409348010","https://openalex.org/W4410609100"],"related_works":["https://openalex.org/W7127121119","https://openalex.org/W7133337262","https://openalex.org/W4415963328","https://openalex.org/W7162044267","https://openalex.org/W7161015496","https://openalex.org/W7101399396","https://openalex.org/W4391590954","https://openalex.org/W4394007075","https://openalex.org/W4416451872","https://openalex.org/W6929628508"],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"extend":[5],"the":[6,46,50,65,71,80,99,109,119,152,164,175],"capacity":[7],"of":[8,49,68,82,121,163,179],"LLMs":[9],"to":[10,32,37,98,145,186],"understand":[11],"multimodal":[12],"information":[13,112],"comprehensively,":[14],"achieving":[15],"remarkable":[16],"performance":[17],"in":[18],"many":[19],"visioncentric":[20],"tasks.Despite":[21],"that,":[22],"recent":[23],"studies":[24],"have":[25,88],"shown":[26],"that":[27,128],"these":[28,93],"models":[29],"are":[30],"susceptible":[31],"jailbreak":[33,85],"attacks,":[34,86,122],"which":[35],"refer":[36],"an":[38],"exploitative":[39],"technique":[40],"where":[41],"malicious":[42],"users":[43],"can":[44,129],"break":[45],"safety":[47],"alignment":[48],"target":[51,165],"model":[52],"and":[53,56,70,158,167,177,189],"generate":[54],"misleading":[55],"harmful":[57,156],"answers.This":[58],"potential":[59],"threat":[60],"is":[61,113,161,193],"caused":[62],"by":[63,76,132],"both":[64,187],"inherent":[66],"vulnerabilities":[67],"LLM":[69],"larger":[72],"attack":[73],"scope":[74],"introduced":[75],"vision":[77],"input.To":[78],"enhance":[79,130],"security":[81],"MLLMs":[83,166],"against":[84],"researchers":[87],"developed":[89],"various":[90],"defense":[91],"techniques.However,":[92],"methods":[94],"either":[95],"require":[96],"modifications":[97],"model's":[100],"internal":[101],"structure":[102],"or":[103],"demand":[104],"significant":[105],"computational":[106],"resources":[107],"during":[108],"inference":[110],"phase.Multimodal":[111],"a":[114,140],"double-edged":[115],"sword.While":[116],"it":[117,123],"increases":[118],"risk":[120],"also":[124],"provides":[125],"additional":[126],"data":[127],"safeguards.Inspired":[131],"this,":[133],"we":[134],"propose":[135],"Cross-modality":[136],"Information":[137],"DEtectoR":[138],"(CIDER),":[139],"plug-andplay":[141],"jailbreaking":[142],"detector":[143],"designed":[144],"identify":[146],"maliciously":[147],"perturbed":[148],"image":[149],"inputs,":[150],"utilizing":[151],"cross-modal":[153],"similarity":[154],"between":[155],"queries":[157],"adversarial":[159],"images.CIDER":[160],"independent":[162],"requires":[168],"less":[169],"computation":[170],"cost.Extensive":[171],"experimental":[172],"results":[173],"demonstrate":[174],"effectiveness":[176],"efficiency":[178],"CIDER,":[180],"as":[181,183],"well":[182],"its":[184],"transferability":[185],"white-box":[188],"blackbox":[190],"MLLMs.The":[191],"resource":[192],"available":[194],"at":[195],"https://github.com/PandragonXIII/CIDER.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-11-28T00:00:00"}