{"id":"https://openalex.org/W4415538021","doi":"https://doi.org/10.1145/3746027.3755715","title":"Transfer Attack for Bad and Good: Explain and Boost Adversarial Transferability across Multimodal Large Language Models","display_name":"Transfer Attack for Bad and Good: Explain and Boost Adversarial Transferability across Multimodal Large Language Models","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538021","doi":"https://doi.org/10.1145/3746027.3755715"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755715","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-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/A5110531341","display_name":"Hao Cheng","orcid":"https://orcid.org/0000-0002-3246-6636"},"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"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Hao Cheng","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and The Hong Kong University of Science and Technology, HongKong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-3246-6636","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and The Hong Kong University of Science and Technology, HongKong SAR, China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081930219","display_name":"Erjia Xiao","orcid":"https://orcid.org/0000-0002-1505-1316"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erjia Xiao","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1505-1316","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056893038","display_name":"Jiayan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayan Yang","raw_affiliation_strings":["The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0006-8532-6895","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jinhao Duan","orcid":"https://orcid.org/0000-0002-6546-8136"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinhao Duan","raw_affiliation_strings":["University of North Carolina at Chapel Hill, Chapel Hill, USA"],"raw_orcid":"https://orcid.org/0000-0002-6546-8136","affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill, Chapel Hill, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595327","display_name":"Yichi Wang","orcid":"https://orcid.org/0009-0000-7986-2209"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichi Wang","raw_affiliation_strings":["Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-7986-2209","affiliations":[{"raw_affiliation_string":"Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015422529","display_name":"Jiahang Cao","orcid":"https://orcid.org/0000-0003-4338-4414"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahang Cao","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4338-4414","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiang Zhang","orcid":"https://orcid.org/0009-0002-8277-1898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiang Zhang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-8277-1898","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015605020","display_name":"Le Yang","orcid":"https://orcid.org/0000-0001-8379-4915"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Yang","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-8379-4915","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102775611","display_name":"Kaidi Xu","orcid":"https://orcid.org/0000-0003-4437-0671"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaidi Xu","raw_affiliation_strings":["Drexel University, Philadelphia, USA"],"raw_orcid":"https://orcid.org/0000-0003-4437-0671","affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055994909","display_name":"Jindong Gu","orcid":"https://orcid.org/0009-0000-0574-0129"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jindong Gu","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0000-0574-0129","affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016140857","display_name":"Renjing Xu","orcid":"https://orcid.org/0000-0002-0792-8974"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renjing Xu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0792-8974","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5110531341"],"corresponding_institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15595312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5010","last_page":"5019"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9970999956130981,"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/T10028","display_name":"Topic Modeling","score":0.9970999956130981,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9955000281333923,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9546999931335449,"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/transferability","display_name":"Transferability","score":0.9377999901771545},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.9108999967575073},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6419000029563904},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.37709999084472656},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3610000014305115},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.33410000801086426},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.3228999972343445}],"concepts":[{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.9377999901771545},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9108999967575073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210999727249146},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6419000029563904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5684000253677368},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46239998936653137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4097999930381775},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34599998593330383},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.29350000619888306},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755715","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2962847335","https://openalex.org/W2962858109","https://openalex.org/W2969542116","https://openalex.org/W4390889737","https://openalex.org/W4393157467"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"demonstrate":[5],"exceptional":[6],"performance":[7],"in":[8,58,106],"cross-modality":[9],"interaction,":[10],"yet":[11],"they":[12],"also":[13],"suffer":[14],"adversarial":[15,22,37,97],"vulnerabilities.":[16],"In":[17,28],"particular,":[18],"the":[19,34,43,53,62,94,103,107],"transferability":[20,38,54,95],"of":[21,36,55,96],"examples":[23,98],"remains":[24],"an":[25],"ongoing":[26],"challenge.":[27],"this":[29,48],"paper,":[30],"we":[31,110],"specifically":[32],"analyze":[33],"manifestation":[35],"among":[39],"MLLMs":[40,56],"and":[41,66,86,119,127],"identify":[42],"key":[44,69],"factors":[45],"that":[46,52,71,114],"influence":[47,73],"characteristic.":[49],"We":[50,75],"discover":[51],"exists":[57],"cross-LLM":[59],"scenarios":[60],"with":[61],"same":[63],"vision":[64],"encoder":[65],"indicate":[67],"two":[68,77,112],"Factors":[70],"may":[72],"transferability.":[74],"provide":[76],"semantic-level":[78],"data":[79],"augmentation":[80],"methods,":[81],"Adding":[82],"Image":[83],"Patch":[84],"(AIP)":[85],"Typography":[87],"Augment":[88],"Transferability":[89],"Method":[90],"(TATM),":[91],"which":[92],"boost":[93],"across":[99],"MLLMs.":[100],"To":[101],"explore":[102],"potential":[104],"impact":[105],"real":[108],"world,":[109],"utilize":[111],"tasks":[113],"can":[115],"have":[116],"both":[117],"negative":[118],"positive":[120],"societal":[121],"impacts:":[122],"1.":[123],"Harmful":[124],"Content":[125],"Insertion":[126],"2.":[128],"Information":[129],"Protection.":[130]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}