{"id":"https://openalex.org/W7154473375","doi":"https://doi.org/10.48550/arxiv.2604.11843","title":"UniMark: Unified Adaptive Multi-bit Watermarking for Autoregressive Image Generators","display_name":"UniMark: Unified Adaptive Multi-bit Watermarking for Autoregressive Image Generators","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7154473375","doi":"https://doi.org/10.48550/arxiv.2604.11843"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.11843","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11843","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.11843","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133683304","display_name":"Yigit Yilmaz","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yilmaz, Yigit","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033771920","display_name":"\u0415\u043b\u0435\u043d\u0430 \u041f\u0435\u0442\u0440\u043e\u0432\u0430","orcid":"https://orcid.org/0000-0002-6417-9498"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petrova, Elena","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100631239","display_name":"Mehmet Kaya","orcid":"https://orcid.org/0000-0003-2995-8282"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaya, Mehmet","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133692847","display_name":"Lucia Rossi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rossi, Lucia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133712470","display_name":"Amir Rahman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rahman, Amir","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5133683304"],"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":0.8413000106811523,"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":0.8413000106811523,"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":0.058400001376867294,"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":0.03319999948143959,"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/digital-watermarking","display_name":"Digital watermarking","score":0.7440000176429749},{"id":"https://openalex.org/keywords/watermark","display_name":"Watermark","score":0.7336000204086304},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.6722999811172485},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5953999757766724},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5115000009536743},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4632999897003174},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4318999946117401},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40549999475479126},{"id":"https://openalex.org/keywords/jpeg","display_name":"JPEG","score":0.3582000136375427}],"concepts":[{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.7440000176429749},{"id":"https://openalex.org/C164112704","wikidata":"https://www.wikidata.org/wiki/Q7974348","display_name":"Watermark","level":3,"score":0.7336000204086304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6915000081062317},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.6722999811172485},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5953999757766724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5342000126838684},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5115000009536743},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4632999897003174},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4318999946117401},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.427700012922287},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4002000093460083},{"id":"https://openalex.org/C198751489","wikidata":"https://www.wikidata.org/wiki/Q2195","display_name":"JPEG","level":3,"score":0.3582000136375427},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.35429999232292175},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.3402000069618225},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3382999897003174},{"id":"https://openalex.org/C193828747","wikidata":"https://www.wikidata.org/wiki/Q864118","display_name":"Binary image","level":4,"score":0.3359000086784363},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3269999921321869},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.322299987077713},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C131521367","wikidata":"https://www.wikidata.org/wiki/Q625502","display_name":"Parity bit","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C169334058","wikidata":"https://www.wikidata.org/wiki/Q353292","display_name":"Additive white Gaussian noise","level":3,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.11843","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11843","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.11843","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.11843","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Invisible":[0],"watermarking":[1,87],"for":[2,36,70,89,147],"autoregressive":[3,90],"(AR)":[4],"image":[5,16,91,122,200],"generation":[6],"has":[7],"recently":[8],"gained":[9],"attention":[10],"as":[11],"a":[12,84,117],"means":[13],"of":[14],"protecting":[15],"ownership":[17],"and":[18,65,116,125,138,151,170,184,206,222],"tracing":[19],"AI-generated":[20],"content.":[21],"However,":[22],"existing":[23],"approaches":[24],"suffer":[25],"from":[26],"three":[27,96,100,190],"key":[28],"limitations:":[29],"(1)":[30],"they":[31,47,67],"embed":[32],"only":[33],"zero-bit":[34],"watermarks":[35],"binary":[37],"verification,":[38],"lacking":[39],"the":[40,61,133,159],"ability":[41],"to":[42,57,75,163],"convey":[43],"multi-bit":[44,207],"messages;":[45],"(2)":[46],"rely":[48],"on":[49,113,180,189],"static":[50],"codebook":[51,110],"partitioning":[52],"strategies":[53],"that":[54,93,157,194],"are":[55,68],"vulnerable":[56],"security":[58],"attacks":[59],"once":[60],"partition":[62],"is":[63],"exposed;":[64],"(3)":[66],"designed":[69],"specific":[71],"AR":[72,79,191],"architectures,":[73],"failing":[74],"generalize":[76],"across":[77,142],"diverse":[78],"paradigms.":[80,175],"We":[81,176],"propose":[82],"\\method{},":[83],"training-free,":[85],"unified":[86],"framework":[88],"generators":[92],"addresses":[94],"all":[95],"limitations.":[97],"\\method{}":[98,195],"introduces":[99],"core":[101],"components:":[102],"\\textbf{Adaptive":[103],"Semantic":[104],"Grouping":[105],"(ASG)},":[106],"which":[107,131],"dynamically":[108],"partitions":[109],"entries":[111],"based":[112],"semantic":[114],"similarity":[115],"secret":[118],"key,":[119],"ensuring":[120],"both":[121,165],"quality":[123,201],"preservation":[124],"security;":[126],"\\textbf{Block-wise":[127],"Multi-bit":[128],"Encoding":[129],"(BME)},":[130],"divides":[132],"token":[134],"sequence":[135],"into":[136],"blocks":[137,143],"encodes":[139],"different":[140],"bits":[141],"with":[144],"error-correcting":[145],"codes":[146],"reliable":[148],"message":[149,208],"transmission;":[150],"\\textbf{a":[152],"Unified":[153],"Token-Replacement":[154],"Interface":[155],"(UTRI)}":[156],"abstracts":[158],"watermark":[160,203],"embedding":[161,185],"process":[162],"support":[164],"next-token":[166],"prediction":[167,172],"(e.g.,":[168,173],"LlamaGen)":[169],"next-scale":[171],"VAR)":[174],"provide":[177],"theoretical":[178],"analysis":[179],"detection":[181,204],"error":[182],"rates":[183],"capacity.":[186],"Extensive":[187],"experiments":[188],"models":[192],"demonstrate":[193],"achieves":[196],"state-of-the-art":[197],"performance":[198],"in":[199],"(FID),":[202],"accuracy,":[205],"extraction,":[209],"while":[210],"maintaining":[211],"robustness":[212],"against":[213],"cropping,":[214],"JPEG":[215],"compression,":[216],"Gaussian":[217],"noise,":[218],"blur,":[219],"color":[220],"jitter,":[221],"random":[223],"erasing":[224],"attacks.":[225]},"counts_by_year":[],"updated_date":"2026-04-16T06:09:31.884825","created_date":"2026-04-16T00:00:00"}