{"id":"https://openalex.org/W7154142409","doi":"https://doi.org/10.1109/tifs.2026.3683292","title":"Transferable Adversarial Attack on Referring Video Object Segmentation","display_name":"Transferable Adversarial Attack on Referring Video Object Segmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7154142409","doi":"https://doi.org/10.1109/tifs.2026.3683292"},"language":null,"primary_location":{"id":"doi:10.1109/tifs.2026.3683292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2026.3683292","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"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 Transactions on Information Forensics and Security","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/A5008576040","display_name":"Meiwen Ding","orcid":"https://orcid.org/0009-0003-7897-581X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Meiwen Ding","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133510992","display_name":"Song Xia","orcid":"https://orcid.org/0009-0002-1224-470X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Song Xia","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore"],"raw_orcid":"https://orcid.org/0009-0002-1224-470X","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116592774","display_name":"Yi Yu","orcid":"https://orcid.org/0000-0003-2730-9553"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yi Yu","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-2730-9553","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085200012","display_name":"Shuting He","orcid":"https://orcid.org/0000-0002-1582-5684"},"institutions":[{"id":"https://openalex.org/I181679659","display_name":"Shanghai University of Finance and Economics","ror":"https://ror.org/00wtvfq62","country_code":"CN","type":"education","lineage":["https://openalex.org/I181679659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuting He","raw_affiliation_strings":["Shanghai University of Finance and Economics, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University of Finance and Economics, Shanghai, China","institution_ids":["https://openalex.org/I181679659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085533260","display_name":"Xudong Jiang","orcid":"https://orcid.org/0000-0002-9104-2315"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xudong Jiang","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-9104-2315","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008576040"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82707491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":null,"first_page":"3989","last_page":"4004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9480999708175659,"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":0.9480999708175659,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0052999998442828655,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.003700000001117587,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7250000238418579},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5892000198364258},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5378999710083008},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5019999742507935},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.38519999384880066},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.3682999908924103},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35260000824928284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8424999713897705},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7250000238418579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6435999870300293},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6079999804496765},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5892000198364258},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5378999710083008},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5019999742507935},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.38519999384880066},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3682999908924103},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3190999925136566},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.2838999927043915},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tifs.2026.3683292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2026.3683292","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"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 Transactions on Information Forensics and Security","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.509709894657135,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Referring":[0],"video":[1,19,65,186],"object":[2,66],"segmentation":[3,67],"(RVOS)":[4],"is":[5,103],"an":[6],"emerging":[7],"task":[8],"that":[9,45],"aims":[10],"to":[11,49,107,129,157,178],"segment":[12],"the":[13,17,69,86,91,168,180,184,189,203],"text-referred":[14],"objects":[15],"in":[16,27],"given":[18],"sequence.":[20],"This":[21,82],"capability":[22],"plays":[23],"a":[24,121,151],"critical":[25],"role":[26],"some":[28,58],"real-world":[29],"safety-critical":[30],"applications":[31],"such":[32,77],"as":[33],"autonomous":[34],"driving.":[35],"However,":[36],"advanced":[37],"RVOS":[38,74,95,102,132,200],"models":[39,75,133,201],"predominantly":[40],"leverage":[41],"deep":[42],"neural":[43],"networks":[44],"are":[46],"inherently":[47],"vulnerable":[48],"adversarial":[50,62,92,190],"perturbations,":[51],"which":[52],"raises":[53],"serious":[54],"safety":[55],"concerns.":[56],"Although":[57],"studies":[59],"have":[60],"explored":[61],"attacks":[63,78],"on":[64,114,194],"(VOS),":[68],"robustness":[70,93],"and":[71,111,137,146,149,187,197,208],"security":[72],"of":[73,94,212],"against":[76],"remain":[79],"insufficiently":[80],"investigated.":[81],"work":[83],"thus,":[84],"for":[85],"first":[87],"time,":[88],"comprehensively":[89],"investigates":[90],"models.":[96],"Distinct":[97],"from":[98],"other":[99],"VOS":[100],"tasks,":[101],"more":[104],"challenging":[105],"due":[106],"its":[108],"multi-modal":[109],"nature":[110],"high":[112],"dependence":[113],"spatial-temporal":[115,169],"information.":[116],"Considering":[117],"that,":[118],"we":[119],"propose":[120],"cross-prompt":[122,152],"Multimodal":[123],"attack":[124,206],"with":[125],"Inter-Clip":[126],"Momentum":[127],"(xM-ICM)":[128],"effectively":[130],"mislead":[131],"under":[134],"both":[135],"white-box":[136,205],"black-box":[138,210],"scenarios.":[139],"The":[140,164],"proposed":[141,214],"xM":[142],"jointly":[143],"corrupts":[144],"visual":[145],"textual":[147],"embeddings":[148],"integrates":[150],"strategy":[153],"during":[154],"iterative":[155],"optimization":[156],"enhance":[158],"generalization":[159],"across":[160,171],"diverse":[161],"linguistic":[162],"queries.":[163],"ICM":[165],"module":[166],"harnesses":[167],"dependencies":[170],"sequence":[172],"clips":[173],"via":[174],"two":[175],"momentum":[176],"banks":[177],"preserve":[179],"perturbation":[181],"coherence":[182],"throughout":[183],"whole":[185],"stabilize":[188],"optimization.":[191],"Experimental":[192],"results":[193],"three":[195],"benchmarks":[196],"five":[198],"prevalent":[199],"demonstrate":[202],"superior":[204],"performance":[207],"strong":[209],"transferability":[211],"our":[213],"method.":[215]},"counts_by_year":[],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2026-04-14T00:00:00"}