{"id":"https://openalex.org/W7129652119","doi":"https://doi.org/10.48550/arxiv.2602.13541","title":"DWBench: Holistic Evaluation of Watermark for Dataset Copyright Auditing","display_name":"DWBench: Holistic Evaluation of Watermark for Dataset Copyright Auditing","publication_year":2026,"publication_date":"2026-02-14","ids":{"openalex":"https://openalex.org/W7129652119","doi":"https://doi.org/10.48550/arxiv.2602.13541"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.13541","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":null,"license_id":null,"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/A5100867251","display_name":"Xiao Ren","orcid":"https://orcid.org/0009-0001-1099-3208"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ren, Xiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126243819","display_name":"Xinyi Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Xinyi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076891548","display_name":"Linkang Du","orcid":"https://orcid.org/0009-0004-9028-9326"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Linkang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126270929","display_name":"Min Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Min","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126267680","display_name":"Yuanchao Shu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shu, Yuanchao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126239514","display_name":"Zhou Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Zhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126249056","display_name":"Yunjun Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Yunjun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126185152","display_name":"Zhikun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhikun","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100867251"],"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":0.6834999918937683,"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":0.6834999918937683,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.034299999475479126,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0340999998152256,"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/watermark","display_name":"Watermark","score":0.9329000115394592},{"id":"https://openalex.org/keywords/digital-watermarking","display_name":"Digital watermarking","score":0.6406999826431274},{"id":"https://openalex.org/keywords/audit","display_name":"Audit","score":0.6087999939918518},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6057000160217285},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.4537999927997589},{"id":"https://openalex.org/keywords/confidentiality","display_name":"Confidentiality","score":0.42480000853538513},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.40389999747276306},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.39089998602867126}],"concepts":[{"id":"https://openalex.org/C164112704","wikidata":"https://www.wikidata.org/wiki/Q7974348","display_name":"Watermark","level":3,"score":0.9329000115394592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544000148773193},{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.6406999826431274},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.6087999939918518},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6057000160217285},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40389999747276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3946000039577484},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3824999928474426},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.34360000491142273},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3402999937534332},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3352999985218048},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3043999969959259},{"id":"https://openalex.org/C112789634","wikidata":"https://www.wikidata.org/wiki/Q18207010","display_name":"False positives and false negatives","level":3,"score":0.28130000829696655},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2989486834","wikidata":"https://www.wikidata.org/wiki/Q3808900","display_name":"True positive rate","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.13541","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.13541","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.13541","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.2602.13541","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"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":{"The":[0],"surging":[1],"demand":[2],"for":[3,13,33,80,93,144,152],"large-scale":[4],"datasets":[5],"in":[6,100,189,207,216],"deep":[7],"learning":[8],"has":[9],"heightened":[10],"the":[11,18,27,127,136,217],"need":[12],"effective":[14],"copyright":[15,214],"protection,":[16],"given":[17],"risks":[19],"of":[20,51,129,138,219],"unauthorized":[21],"use":[22],"to":[23,125],"data":[24,222],"owners.":[25],"Although":[26],"dataset":[28,97],"watermark":[29,98,146,186,208],"technique":[30],"holds":[31],"promise":[32],"auditing":[34],"and":[35,49,90,102,120,148,158,173,179,188,210],"verifying":[36],"usage,":[37],"existing":[38,180],"methods":[39,65,111],"are":[40],"hindered":[41],"by":[42,66],"inconsistent":[43],"evaluations,":[44],"which":[45,155],"impede":[46],"fair":[47],"comparisons":[48],"assessments":[50],"real-world":[52],"viability.":[53],"To":[54],"address":[55],"this":[56],"gap,":[57],"we":[58,84,107,134],"propose":[59],"a":[60,77,87],"two-layer":[61],"taxonomy":[62],"that":[63,202],"categorizes":[64],"implementation":[67],"(model-based":[68],"vs.":[69,73],"model-free":[70],"injection;":[71],"model-behavior":[72],"model-message":[74],"verification),":[75],"offering":[76],"structured":[78],"framework":[79],"cross-task":[81],"analysis.":[82],"Then,":[83],"develop":[85],"DWBench,":[86,106],"unified":[88],"benchmark":[89],"open-source":[91],"toolkit":[92],"systematically":[94],"evaluating":[95],"image":[96],"techniques":[99,181],"classification":[101,172],"generation":[103,174],"tasks.":[104],"Using":[105],"assess":[108],"25":[109],"representative":[110],"under":[112],"standardized":[113],"conditions,":[114],"perturbation-based":[115],"robustness":[116],"tests,":[117],"multi-watermark":[118],"coexistence,":[119],"multi-user":[121,191],"interference.":[122],"In":[123],"addition":[124],"reporting":[126],"results":[128,137],"four":[130],"commonly":[131],"used":[132],"metrics,":[133],"present":[135],"two":[139],"new":[140],"metrics:":[141],"sample":[142],"significance":[143],"fine-grained":[145],"distinguishability":[147],"verification":[149],"success":[150],"rate":[151],"dataset-level":[153],"auditing,":[154],"enable":[156],"accurate":[157],"reproducible":[159],"benchmarking.":[160],"Key":[161],"findings":[162],"reveal":[163],"inherent":[164],"trade-offs:":[165],"no":[166],"single":[167],"method":[168],"dominates":[169],"all":[170],"scenarios;":[171],"tasks":[175],"require":[176],"specialized":[177],"approaches;":[178],"exhibit":[182],"instability":[183],"at":[184],"low":[185],"rates":[187],"realistic":[190],"settings,":[192],"with":[193],"elevated":[194],"false":[195],"positives":[196],"or":[197],"performance":[198],"declines.":[199],"We":[200],"hope":[201],"DWBench":[203],"can":[204],"facilitate":[205],"advances":[206],"reliability":[209],"practicality,":[211],"thus":[212],"strengthening":[213],"safeguards":[215],"face":[218],"widespread":[220],"AI-driven":[221],"exploitation.":[223]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-18T00:00:00"}