{"id":"https://openalex.org/W7136574632","doi":"https://doi.org/10.48550/arxiv.2603.12749","title":"SLICE: Semantic Latent Injection via Compartmentalized Embedding for Image Watermarking","display_name":"SLICE: Semantic Latent Injection via Compartmentalized Embedding for Image Watermarking","publication_year":2026,"publication_date":"2026-03-13","ids":{"openalex":"https://openalex.org/W7136574632","doi":"https://doi.org/10.48550/arxiv.2603.12749"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.12749","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.12749","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.12749","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129640378","display_name":"Zheng Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129545860","display_name":"Yifan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129484149","display_name":"Xiaoyu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiaoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129538050","display_name":"Xiaoyan Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Xiaoyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048679870","display_name":"Haoran Fan","orcid":"https://orcid.org/0009-0008-7745-4170"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129524768","display_name":"Yang Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129548039","display_name":"Jiaojiao Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Jiaojiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.4309999942779541,"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/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.4309999942779541,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.13609999418258667,"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":0.12999999523162842,"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/digital-watermarking","display_name":"Digital watermarking","score":0.8131999969482422},{"id":"https://openalex.org/keywords/watermark","display_name":"Watermark","score":0.6531000137329102},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6028000116348267},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5993000268936157},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5881999731063843},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5773000121116638},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.414000004529953},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.37450000643730164}],"concepts":[{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.8131999969482422},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7080000042915344},{"id":"https://openalex.org/C164112704","wikidata":"https://www.wikidata.org/wiki/Q7974348","display_name":"Watermark","level":3,"score":0.6531000137329102},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6028000116348267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6015999913215637},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5993000268936157},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5881999731063843},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5773000121116638},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41909998655319214},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.37450000643730164},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.37049999833106995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.33399999141693115},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29510000348091125},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.2800999879837036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26429998874664307},{"id":"https://openalex.org/C204806902","wikidata":"https://www.wikidata.org/wiki/Q2333581","display_name":"Semantic security","level":5,"score":0.25920000672340393}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.12749","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.12749","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.12749","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.12749","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Watermarking":[0],"the":[1,100],"initial":[2,101],"noise":[3,18],"of":[4],"diffusion":[5],"models":[6],"has":[7],"emerged":[8],"as":[9],"a":[10,44,65,165],"promising":[11],"approach":[12],"for":[13],"image":[14,38,81,157],"provenance,":[15],"but":[16,54],"content-independent":[17],"patterns":[19],"can":[20],"be":[21],"forged":[22],"via":[23,74],"inversion":[24],"and":[25,63,90,92,117,126,130,159,176],"regeneration":[26,149],"attacks.":[27],"Recent":[28],"semantic-aware":[29,67],"watermarking":[30],"methods":[31],"improve":[32],"robustness":[33],"by":[34],"conditioning":[35],"verification":[36,111],"on":[37,43,134],"semantics.":[39],"However,":[40],"their":[41],"reliance":[42],"single":[45],"global":[46],"semantic":[47,57,85,106,113,160],"binding":[48,107],"makes":[49],"them":[50,95],"vulnerable":[51],"to":[52,96,178],"localized":[53],"globally":[55],"coherent":[56],"edits.":[58],"To":[59],"address":[60],"this":[61],"limitation":[62],"provide":[64],"trustworthy":[66],"watermark,":[68],"we":[69],"propose":[70],"$\\underline{\\textbf{S}}$emantic":[71],"$\\underline{\\textbf{L}}$atent":[72],"$\\underline{\\textbf{I}}$njection":[73],"$\\underline{\\textbf{C}}$ompartmentalized":[75],"$\\underline{\\textbf{E}}$mbedding":[76],"($\\textbf{SLICE}$).":[77],"Our":[78],"framework":[79],"decouples":[80],"semantics":[82],"into":[83],"four":[84],"factors":[86],"(subject,":[87],"environment,":[88],"action,":[89],"detail)":[91],"precisely":[93],"anchors":[94],"distinct":[97],"regions":[98],"in":[99,174],"Gaussian":[102],"noise.":[103],"This":[104],"fine-grained":[105,173],"enables":[108,124],"advanced":[109,147],"watermark":[110],"where":[112],"tampering":[114],"is":[115,171],"detectable":[116],"localizable.":[118],"We":[119],"theoretically":[120],"justify":[121],"why":[122],"SLICE":[123,141,163],"robust":[125,177],"reliable":[127],"tamper":[128],"localization":[129],"provides":[131],"statistical":[132],"guarantees":[133],"false-accept":[135],"rates.":[136],"Experimental":[137],"results":[138],"demonstrate":[139],"that":[140,170],"significantly":[142],"outperforms":[143],"existing":[144],"baselines":[145],"against":[146],"semantic-guided":[148],"attacks,":[150],"substantially":[151],"reducing":[152],"attack":[153],"success":[154],"while":[155],"preserving":[156],"quality":[158],"fidelity.":[161],"Overall,":[162],"offers":[164],"practical,":[166],"training-free":[167],"provenance":[168],"solution":[169],"both":[172],"diagnosis":[175],"realistic":[179],"adversarial":[180],"manipulations.":[181]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-17T00:00:00"}