{"id":"https://openalex.org/W4415536837","doi":"https://doi.org/10.1145/3746027.3754951","title":"Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations","display_name":"Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536837","doi":"https://doi.org/10.1145/3746027.3754951"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754951","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754951","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":"conference-paper","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/A5086139931","display_name":"Jinjie Shen","orcid":"https://orcid.org/0009-0000-0334-1669"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinjie Shen","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0000-0334-1669","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101651167","display_name":"Yaxiong Wang","orcid":"https://orcid.org/0000-0001-6596-8117"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxiong Wang","raw_affiliation_strings":["Hefei University of Technology, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-6596-8117","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060524512","display_name":"Lechao Cheng","orcid":"https://orcid.org/0000-0002-7546-9052"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lechao Cheng","raw_affiliation_strings":["Hefei University of Technology, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-7546-9052","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049953967","display_name":"Nan Pu","orcid":"https://orcid.org/0000-0002-2179-8301"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nan Pu","raw_affiliation_strings":["University of Trento, Trento, Trentino, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2179-8301","affiliations":[{"raw_affiliation_string":"University of Trento, Trento, Trentino, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065328976","display_name":"Zhun Zhong","orcid":"https://orcid.org/0000-0002-8202-0544"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhun Zhong","raw_affiliation_strings":["Hefei University of Technology, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-8202-0544","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, Anhui, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11308","last_page":"11317"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9912999868392944,"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/T12031","display_name":"Speech and dialogue systems","score":0.9912999868392944,"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/T10028","display_name":"Topic Modeling","score":0.9882000088691711,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9760000109672546,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.5827999711036682},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.5085999965667725},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5019000172615051},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4431000053882599},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.36579999327659607},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.36469998955726624},{"id":"https://openalex.org/keywords/image-manipulation","display_name":"Image manipulation","score":0.35179999470710754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7753999829292297},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5827999711036682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5485000014305115},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.5085999965667725},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5019000172615051},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4431000053882599},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.36579999327659607},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.36469998955726624},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.35179999470710754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33709999918937683},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3296000063419342},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.31940001249313354},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28929999470710754},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2671000063419342},{"id":"https://openalex.org/C2983589003","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text detection","level":3,"score":0.2551000118255615},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754951","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754951","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":[{"id":"https://openalex.org/G5784255744","display_name":null,"funder_award_id":"JZ2024HGTB0261","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2965848243","https://openalex.org/W2998163473","https://openalex.org/W3088460296","https://openalex.org/W4312350393","https://openalex.org/W4384918448","https://openalex.org/W4399251441","https://openalex.org/W4403853618","https://openalex.org/W4405655184","https://openalex.org/W4407794264","https://openalex.org/W4412377189","https://openalex.org/W6891899813","https://openalex.org/W6947991961"],"related_works":[],"abstract_inverted_index":{"The":[0,183],"detection":[1,62,157,175],"and":[2,122,143,154,185],"grounding":[3,153],"of":[4,63,103],"manipulated":[5],"content":[6],"in":[7,16],"multimodal":[8],"data":[9],"has":[10],"emerged":[11],"as":[12,139],"a":[13,91,118],"critical":[14],"challenge":[15],"media":[17],"forensics.":[18],"While":[19],"existing":[20,170],"benchmarks":[21],"demonstrate":[22,165],"technical":[23],"progress,":[24],"they":[25],"suffer":[26],"from":[27],"misalignment":[28],"artifacts":[29],"that":[30,107],"poorly":[31],"reflect":[32],"real-world":[33],"manipulation":[34,156],"patterns:":[35],"practical":[36],"attacks":[37],"typically":[38],"maintain":[39],"semantic":[40],"consistency":[41],"across":[42],"modalities,":[43],"whereas":[44],"current":[45],"datasets":[46],"artificially":[47],"disrupt":[48],"cross-modal":[49],"alignment,":[50],"creating":[51],"easily":[52],"detectable":[53],"anomalies.":[54],"To":[55],"bridge":[56],"this":[57,114],"gap,":[58],"we":[59,116],"pioneer":[60],"the":[61,82,109,140,147],"semantically-coordinated":[64],"manipulations":[65],"where":[66],"visual":[67,110],"edits":[68],"are":[69,187],"systematically":[70],"paired":[71],"with":[72,80,146],"semantically":[73],"consistent":[74],"textual":[75,105],"descriptions.":[76],"Our":[77],"approach":[78],"begins":[79],"constructing":[81],"first":[83],"Semantic-Aligned":[84],"Multimodal":[85],"Manipulation":[86,120],"(SAMM)":[87],"dataset,":[88],"generated":[89],"through":[90,149],"two-stage":[92],"pipeline:":[93],"1)":[94],"applying":[95],"state-of-the-art":[96,181],"image":[97,151],"manipulations,":[98],"followed":[99],"by":[100,128],"2)":[101],"generation":[102],"contextually-plausible":[104],"narratives":[106],"reinforce":[108],"deception.":[111],"Building":[112],"on":[113,177],"foundation,":[115],"propose":[117],"Retrieval-Augmented":[119],"Detection":[121],"Grounding":[123],"(RamDG)":[124],"framework.":[125],"RamDG":[126],"commences":[127],"harnessing":[129],"external":[130],"knowledge":[131],"repositories":[132],"to":[133,159,180],"retrieve":[134],"contextual":[135],"evidence,":[136],"which":[137],"serves":[138],"auxiliary":[141],"texts":[142],"encoded":[144],"together":[145],"inputs":[148],"our":[150,166],"forgery":[152],"deep":[155],"modules":[158],"trace":[160],"all":[161],"manipulations.":[162],"Extensive":[163],"experiments":[164],"framework":[167],"significantly":[168],"outperforms":[169],"methods,":[171],"achieving":[172],"2.06%":[173],"higher":[174],"accuracy":[176],"SAMM":[178],"compared":[179],"approaches.":[182],"dataset":[184],"code":[186],"publicly":[188],"available":[189],"at":[190],"https://github.com/shen8424/SAMM-RamDG-CAP.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}