{"id":"https://openalex.org/W7152693487","doi":"https://doi.org/10.1145/3774904.3792315","title":"Breaking Cross-modal Alignment in Embodied Intelligence: A Multimodal Adversarial Attack Framework for Vision-Language-Action Models","display_name":"Breaking Cross-modal Alignment in Embodied Intelligence: A Multimodal Adversarial Attack Framework for Vision-Language-Action Models","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152693487","doi":"https://doi.org/10.1145/3774904.3792315"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792315","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792315","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792315","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133285769","display_name":"Zhihui Zhao","orcid":"https://orcid.org/0009-0007-0695-1199"},"institutions":[{"id":"https://openalex.org/I46305995","display_name":"Taiyuan University of Science and Technology","ror":"https://ror.org/01wcbdc92","country_code":"CN","type":"education","lineage":["https://openalex.org/I46305995"]},{"id":"https://openalex.org/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihui Zhao","raw_affiliation_strings":["College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Taiyuan, Shanxi, China and State Key Laboratory of Internet Architecture, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-0695-1199","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Taiyuan, Shanxi, China and State Key Laboratory of Internet Architecture, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I9086337","https://openalex.org/I46305995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079397042","display_name":"Xiaorong Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I46305995","display_name":"Taiyuan University of Science and Technology","ror":"https://ror.org/01wcbdc92","country_code":"CN","type":"education","lineage":["https://openalex.org/I46305995"]},{"id":"https://openalex.org/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaorong Dong","raw_affiliation_strings":["College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Industrial Internet Security, Taiyuan, China"],"raw_orcid":"https://orcid.org/0009-0007-1337-1678","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Industrial Internet Security, Taiyuan, China","institution_ids":["https://openalex.org/I9086337","https://openalex.org/I46305995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053886363","display_name":"Yaowen Zheng","orcid":"https://orcid.org/0000-0002-8953-0782"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaowen Zheng","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8953-0782","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103103151","display_name":"Xiaohui Chen","orcid":"https://orcid.org/0000-0002-3921-7907"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Chen","raw_affiliation_strings":["China Mobile Research Institute, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3921-7907","affiliations":[{"raw_affiliation_string":"China Mobile Research Institute, Beijing, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045009020","display_name":"Yimo Ren","orcid":"https://orcid.org/0000-0002-7543-0326"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yimo Ren","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7543-0326","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101322783","display_name":"Hangbei Cheng","orcid":"https://orcid.org/0009-0006-7310-7636"},"institutions":[{"id":"https://openalex.org/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangbei Cheng","raw_affiliation_strings":["College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Taiyuan, Shanxi, China"],"raw_orcid":"https://orcid.org/0009-0006-7310-7636","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology (College of Data Science), Taiyuan University of Technology, Taiyuan, Shanxi, China","institution_ids":["https://openalex.org/I9086337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077607914","display_name":"Yongle Chen","orcid":"https://orcid.org/0000-0002-1000-1109"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]},{"id":"https://openalex.org/I9086337","display_name":"Taiyuan University of Technology","ror":"https://ror.org/03kv08d37","country_code":"CN","type":"education","lineage":["https://openalex.org/I9086337"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongle Chen","raw_affiliation_strings":["College of Artificial Intelligence, Taiyuan University of Technology, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Industrial Internet Security, Taiyuan, Shanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-1000-1109","affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Taiyuan University of Technology, Taiyuan, Shanxi, China and Shanxi Key Laboratory of Industrial Internet Security, Taiyuan, Shanxi, China","institution_ids":["https://openalex.org/I9086337","https://openalex.org/I181877577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061643975","display_name":"Limin Sun","orcid":"https://orcid.org/0000-0003-2745-7521"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Limin Sun","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2745-7521","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50908148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2824","last_page":"2834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5026000142097473,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5026000142097473,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.17389999330043793,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.04100000113248825,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6643000245094299},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4083000123500824},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.40059998631477356},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2996000051498413},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.2818000018596649},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.2745000123977661}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6643000245094299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6165000200271606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41819998621940613},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4083000123500824},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.27300000190734863},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2556000053882599},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792315","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792315","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792315","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792315","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.405940979719162}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2025011604","https://openalex.org/W2914845116","https://openalex.org/W2963302614","https://openalex.org/W3036069296","https://openalex.org/W3091588028","https://openalex.org/W3216316500","https://openalex.org/W4319866006","https://openalex.org/W4386597063","https://openalex.org/W4387967929","https://openalex.org/W4392172801","https://openalex.org/W4401978387","https://openalex.org/W4408627772"],"related_works":[],"abstract_inverted_index":{"Vision\u2013Language\u2013Action":[0],"(VLA)":[1],"models":[2],"underpin":[3],"robotic":[4],"and":[5,13,84,92,124,154,164,171,181],"other":[6],"embodied":[7,51,169],"agents":[8],"by":[9,141],"mapping":[10],"visual":[11,118],"observations":[12],"language":[14],"instructions":[15],"into":[16,82],"executable":[17],"actions.":[18],"Their":[19],"wide":[20],"adoption":[21],"through":[22],"open":[23],"web":[24],"model":[25],"repositories,":[26],"however,":[27],"introduces":[28],"new":[29],"supply-chain":[30],"risks:":[31],"adversaries":[32],"can":[33],"launch":[34],"adversarial":[35,63],"attacks":[36],"to":[37,46,88,145,168,176],"manipulate":[38],"the":[39,96,134],"action":[40,98],"outputs":[41],"of":[42,138],"VLAs,":[43],"potentially":[44],"leading":[45],"harmful":[47],"real-world":[48,125],"outcomes":[49],"for":[50],"agents.":[52],"To":[53,100],"exploit":[54],"this":[55],"vulnerability,":[56],"we":[57,106],"propose":[58],"MAVLA,":[59],"a":[60,69,76,130,162,173],"novel":[61],"multimodal":[62,114],"attack":[64,102,147,152],"framework.":[65],"MAVLA":[66,149],"serves":[67],"as":[68],"modular":[70],"front-end":[71],"that":[72,111,128],"integrates":[73],"seamlessly":[74],"with":[75,104,156],"target":[77],"VLA":[78,184],"model,":[79],"injecting":[80],"perturbations":[81],"task-relevant":[83],"structure-sensitive":[85],"image":[86],"regions":[87],"disrupt":[89],"cross-modal":[90],"alignment":[91],"induce":[93],"deviations":[94],"in":[95,122],"generated":[97],"instructions.":[99],"balance":[101],"effectiveness":[103,153],"stealth,":[105],"design":[107],"four":[108],"loss":[109],"functions":[110],"jointly":[112],"maximize":[113],"misalignment":[115],"while":[116],"preserving":[117],"stealthiness.":[119],"Extensive":[120],"evaluations":[121],"simulated":[123],"scenarios":[126],"show":[127],"at":[129],"40%":[131],"perturbation":[132],"ratio,":[133],"task":[135],"success":[136],"rate":[137],"VLAs":[139],"drops":[140],"about":[142],"70%.":[143],"Compared":[144],"conventional":[146],"baselines,":[148],"achieves":[150],"superior":[151],"stealthiness":[155],"low":[157],"overhead.":[158],"Our":[159],"work":[160],"reveals":[161],"practical":[163],"previously":[165],"underexplored":[166],"threat":[167],"systems,":[170],"offers":[172],"red-team":[174],"baseline":[175],"inform":[177],"future":[178],"defensive":[179],"strategies":[180],"promote":[182],"safer":[183],"deployment.":[185]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-10T00:00:00"}
