{"id":"https://openalex.org/W7160305654","doi":"https://doi.org/10.48550/arxiv.2605.02557","title":"VertMark: A Unified Training-Free Robust Watermarking Framework for Vertical Domain Pre-trained Language Models","display_name":"VertMark: A Unified Training-Free Robust Watermarking Framework for Vertical Domain Pre-trained Language Models","publication_year":2026,"publication_date":"2026-05-04","ids":{"openalex":"https://openalex.org/W7160305654","doi":"https://doi.org/10.48550/arxiv.2605.02557"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.02557","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.02557","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.02557","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134363674","display_name":"Cong Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong, Cong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135331460","display_name":"Xin Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135397942","display_name":"Zhaoxia Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Zhaoxia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135323762","display_name":"Shuai Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135391479","display_name":"Jie Zhang","orcid":"https://orcid.org/0009-0002-9163-1774"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135400287","display_name":"Weiming Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Weiming","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.6237999796867371,"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":0.6237999796867371,"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":0.05779999867081642,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.03830000013113022,"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":0.9096999764442444},{"id":"https://openalex.org/keywords/backdoor","display_name":"Backdoor","score":0.753000020980835},{"id":"https://openalex.org/keywords/watermark","display_name":"Watermark","score":0.7050999999046326},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6531000137329102},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.635699987411499},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6297000050544739},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46860000491142273}],"concepts":[{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.9096999764442444},{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.753000020980835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7493000030517578},{"id":"https://openalex.org/C164112704","wikidata":"https://www.wikidata.org/wiki/Q7974348","display_name":"Watermark","level":3,"score":0.7050999999046326},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6531000137329102},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.635699987411499},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6297000050544739},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.46889999508857727},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.4352000057697296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4059000015258789},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37049999833106995},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C193470923","wikidata":"https://www.wikidata.org/wiki/Q5276026","display_name":"Digital Watermarking Alliance","level":4,"score":0.32100000977516174},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.288100004196167},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.27129998803138733},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25049999356269836},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.02557","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.02557","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.02557","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.02557","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":"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":{"With":[0],"the":[1,80,144,177],"application":[2],"of":[3,54,180],"vertical":[4,71,93],"domain":[5,94],"pre-trained":[6],"language":[7],"models":[8],"(VPLMs)":[9],"in":[10,143],"specialized":[11],"fields":[12],"such":[13],"as":[14],"medical,":[15,145],"finance,":[16],"and":[17,21,65,84,111,130,138,147,166,172],"law,":[18],"model":[19,154],"parameters":[20],"inference":[22],"capabilities":[23],"have":[24],"become":[25,36],"important":[26],"digital":[27],"assets.":[28],"Achieving":[29],"traceable":[30],"copyright":[31,41,89,178],"verification":[32,42,90,133],"for":[33,69,88,134,176],"VPLMs":[34],"has":[35],"an":[37],"urgent":[38],"challenge.":[39],"Existing":[40],"methods":[43,56],"primarily":[44],"rely":[45],"on":[46,153],"embedding":[47,129],"backdoor":[48],"watermarks":[49,100],"into":[50],"models.":[51],"However,":[52],"most":[53],"these":[55,75],"require":[57],"additional":[58],"training,":[59],"suffer":[60],"from":[61],"inefficient":[62],"watermark":[63,128,132],"embedding,":[64],"lack":[66],"scalable":[67],"designs":[68],"multiple":[70,92],"domains.":[72],"To":[73],"address":[74],"limitations,":[76],"we":[77],"propose":[78],"VertMark,":[79],"first":[81],"unified":[82],"training-free":[83,117],"robust":[85],"watermarking":[86],"framework":[87,97],"across":[91],"VPLMs.":[95,181],"The":[96],"embeds":[98],"ownership-encoded":[99],"by":[101],"establishing":[102],"a":[103,116],"hidden":[104],"semantic":[105],"equivalence":[106],"between":[107],"low-frequency":[108],"trigger":[109],"tokens":[110],"high-frequency":[112],"domain-relevant":[113],"words":[114],"via":[115],"parameter":[118],"replacement":[119],"strategy.":[120],"Experiments":[121],"demonstrate":[122],"that":[123],"VertMark":[124,157],"can":[125],"achieve":[126],"efficient":[127],"reliable":[131],"both":[135],"text":[136,139],"understanding":[137],"generation":[140],"downstream":[141],"tasks":[142],"financial,":[146],"legal":[148],"domains,":[149],"with":[150],"negligible":[151],"impact":[152],"performance.":[155],"Moreover,":[156],"exhibits":[158],"strong":[159,174],"robustness":[160],"against":[161],"various":[162],"attacks":[163],"(e.g.,":[164],"pruning":[165],"quantization),":[167],"highlighting":[168],"its":[169],"practical":[170],"value":[171],"providing":[173],"protection":[175],"security":[179]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-06T00:00:00"}