{"id":"https://openalex.org/W7131657950","doi":"https://doi.org/10.48550/arxiv.2602.21849","title":"Meta-FC: Meta-Learning with Feature Consistency for Robust and Generalizable Watermarking","display_name":"Meta-FC: Meta-Learning with Feature Consistency for Robust and Generalizable Watermarking","publication_year":2026,"publication_date":"2026-02-25","ids":{"openalex":"https://openalex.org/W7131657950","doi":"https://doi.org/10.48550/arxiv.2602.21849"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.21849","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","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":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126855799","display_name":"Yuheng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Yuheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126922268","display_name":"Weitong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Weitong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126883785","display_name":"Chengcheng Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Chengcheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126881710","display_name":"Jiale Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiale","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052951255","display_name":"Chunpeng Ge","orcid":"https://orcid.org/0000-0002-9274-7325"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge, Chunpeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126950470","display_name":"Di Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Di","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Long, Guodong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long, Guodong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5126855799"],"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":0.48919999599456787,"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":0.48919999599456787,"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":0.14249999821186066,"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":0.059300001710653305,"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/robustness","display_name":"Robustness (evolution)","score":0.8561000227928162},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6550999879837036},{"id":"https://openalex.org/keywords/digital-watermarking","display_name":"Digital watermarking","score":0.5728999972343445},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5001000165939331},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4862000048160553},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4562999904155731},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4320000112056732},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.414000004529953}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8561000227928162},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6550999879837036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6118999719619751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6080999970436096},{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.5728999972343445},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5001000165939331},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4862000048160553},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4320000112056732},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3840000033378601},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.37439998984336853},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.34279999136924744},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3418000042438507},{"id":"https://openalex.org/C2986577269","wikidata":"https://www.wikidata.org/wiki/Q11306265","display_name":"Random noise","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.305400013923645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2897999882698059},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.28619998693466187},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.25040000677108765},{"id":"https://openalex.org/C173413354","wikidata":"https://www.wikidata.org/wiki/Q7049470","display_name":"Nonlinear distortion","level":4,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.21849","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.21849","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.21849","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":"pmh:doi:10.48550/arxiv.2602.21849","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/6","score":0.5226044654846191,"display_name":"Clean water and sanitation"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"learning-based":[1],"watermarking":[2,73,213],"has":[3],"made":[4],"remarkable":[5],"progress":[6],"in":[7,35,159],"recent":[8],"years.":[9],"To":[10,77,162],"achieve":[11],"robustness":[12,68,89,208],"against":[13],"various":[14,212],"distortions,":[15,146],"current":[16],"methods":[17],"commonly":[18],"adopt":[19],"a":[20,24,65,83,110,119,175],"training":[21,37,85,203],"strategy":[22,42,86],"where":[23],"\\underline{\\textbf{s}}ingle":[25],"\\underline{\\textbf{r}}andom":[26],"\\underline{\\textbf{d}}istortion":[27],"(SRD)":[28],"is":[29,131],"chosen":[30],"as":[31,118],"the":[32,40,50,67,72,105,124,129,148,153,165,181,185,201,207],"noise":[33,106],"layer":[34],"each":[36,47,160],"batch.":[38,161],"However,":[39],"SRD":[41,202],"treats":[43],"distortions":[44,57,103,158,191],"independently":[45],"within":[46],"batch,":[48],"neglecting":[49],"inherent":[51],"relationships":[52],"among":[53],"different":[54,143,190],"types":[55,144],"of":[56,71,145,156,167,184,211,218],"and":[58,69,90,135,209,221,226],"causing":[59],"optimization":[60,149],"conflicts":[61,150],"across":[62,142],"batches.":[63],"As":[64],"result,":[66],"generalizability":[70],"model":[74,130],"are":[75],"limited.":[76],"address":[78],"this":[79],"issue,":[80],"we":[81,99,173],"propose":[82],"novel":[84],"that":[87,138,179],"enhances":[88],"generalization":[91,210],"via":[92],"\\underline{\\textbf{meta}}-learning":[93],"with":[94],"\\underline{\\textbf{f}}eature":[95],"\\underline{\\textbf{c}}onsistency":[96],"(Meta-FC).":[97],"Specifically,":[98],"randomly":[100],"sample":[101],"multiple":[102],"from":[104],"pool":[107],"to":[108,133,189,192,200],"construct":[109],"meta-training":[111],"task,":[112],"while":[113],"holding":[114],"out":[115],"one":[116],"distortion":[117,122],"simulated":[120],"``unknown''":[121],"for":[123],"meta-testing":[125],"phase.":[126],"Through":[127],"meta-learning,":[128],"encouraged":[132],"identify":[134],"utilize":[136],"neurons":[137],"exhibit":[139],"stable":[140,168],"activations":[141,169],"mitigating":[147],"caused":[151],"by":[152,215],"random":[154],"sampling":[155],"diverse":[157],"further":[163],"promote":[164],"transformation":[166],"into":[170],"distortion-invariant":[171],"representations,":[172],"introduce":[174],"feature":[176],"consistency":[177],"loss":[178],"constrains":[180],"decoded":[182],"features":[183],"same":[186],"image":[187],"subjected":[188],"remain":[193],"consistent.":[194],"Extensive":[195],"experiments":[196],"demonstrate":[197],"that,":[198],"compared":[199],"strategy,":[204],"Meta-FC":[205],"improves":[206],"models":[214],"an":[216],"average":[217],"1.59\\%,":[219],"4.71\\%,":[220],"2.38\\%":[222],"under":[223],"high-intensity,":[224],"combined,":[225],"unknown":[227],"distortions.":[228]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-27T00:00:00"}