{"id":"https://openalex.org/W4403564332","doi":"https://doi.org/10.48550/arxiv.2410.09101","title":"Data Taggants: Dataset Ownership Verification via Harmless Targeted Data Poisoning","display_name":"Data Taggants: Dataset Ownership Verification via Harmless Targeted Data Poisoning","publication_year":2024,"publication_date":"2024-10-09","ids":{"openalex":"https://openalex.org/W4403564332","doi":"https://doi.org/10.48550/arxiv.2410.09101"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.09101","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.09101","pdf_url":"https://arxiv.org/pdf/2410.09101","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.09101","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114331453","display_name":"Wassim Bouaziz","orcid":"https://orcid.org/0009-0000-3597-6247","observed_orcids":["https://orcid.org/0009-0000-3597-6247"]},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210107641","display_name":"Centre de Math\u00e9matiques Appliqu\u00e9es de l'\u00c9cole polytechnique","ror":"https://ror.org/012e1xn46","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210107641","https://openalex.org/I4210141950","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Bouaziz, Wassim","raw_affiliation_strings":["FAIR & CMAP , \u00c9cole polytechnique Paris , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAIR & CMAP , \u00c9cole polytechnique Paris , France","institution_ids":["https://openalex.org/I142476485","https://openalex.org/I4210107641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084360449","display_name":"Nicolas Usunier","orcid":"https://orcid.org/0000-0002-9324-1457","observed_orcids":["https://orcid.org/0000-0002-9324-1457"]},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210107641","display_name":"Centre de Math\u00e9matiques Appliqu\u00e9es de l'\u00c9cole polytechnique","ror":"https://ror.org/012e1xn46","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210107641","https://openalex.org/I4210141950","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Usunier, Nicolas","raw_affiliation_strings":["CMAP , \u00c9cole polytechnique Palaiseau , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CMAP , \u00c9cole polytechnique Palaiseau , France","institution_ids":["https://openalex.org/I142476485","https://openalex.org/I4210107641"]}]},{"author_position":"last","author":{"id":null,"display_name":"El-Mhamdi, El-Mahdi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"El-Mhamdi, El-Mahdi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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":0.9804999828338623,"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":0.9804999828338623,"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/T12122","display_name":"Physical Unclonable Functions (PUFs) and Hardware Security","score":0.005799999926239252,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.004900000058114529,"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/clean-label-attacks","display_name":"clean-label attacks","score":0.6549999713897705},{"id":"https://openalex.org/keywords/out-of-distribution-samples","display_name":"out-of-distribution samples","score":0.847000002861023},{"id":"https://openalex.org/keywords/black-box-verification","display_name":"black-box verification","score":0.5509999990463257},{"id":"https://openalex.org/keywords/data-contamination","display_name":"contaminated data","score":0.5730000138282776},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.5419999957084656},{"id":"https://openalex.org/keywords/resnet","display_name":"ResNet","score":0.5799999833106995}],"concepts":[{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.45250025391578674},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.42733651399612427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4117634892463684},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.3777267038822174},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33961158990859985},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32491132616996765}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.09101","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.09101","pdf_url":"https://arxiv.org/pdf/2410.09101","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.09101","doi":"https://doi.org/10.48550/arxiv.2410.09101","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.09101","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.09101","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.09101","pdf_url":"https://arxiv.org/pdf/2410.09101","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403564332.pdf","grobid_xml":"https://content.openalex.org/works/W4403564332.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2740924709","https://openalex.org/W2765407302","https://openalex.org/W2900018096","https://openalex.org/W3012922053","https://openalex.org/W3083109707","https://openalex.org/W3135766489","https://openalex.org/W3201822691","https://openalex.org/W3211926155","https://openalex.org/W4404340783","https://openalex.org/W4415798785"],"related_works":["https://openalex.org/W7103193417","https://openalex.org/W4362714395","https://openalex.org/W4416683898","https://openalex.org/W7133186737","https://openalex.org/W4417161939","https://openalex.org/W4413145835","https://openalex.org/W7027856197","https://openalex.org/W4383199672","https://openalex.org/W7213370480","https://openalex.org/W4415141405"],"abstract_inverted_index":{"Dataset":[0],"ownership":[1,90],"verification,":[2],"the":[3,40,47,61,69,125,129,148,182,201],"process":[4],"of":[5,46,97,205],"determining":[6],"if":[7],"a":[8,13,36,44,86,115],"dataset":[9,89,184],"is":[10,17],"used":[11],"in":[12],"model's":[14,62,70],"training":[15,168],"data,":[16],"necessary":[18],"for":[19,140],"detecting":[20],"unauthorized":[21],"data":[22,25,48,84,110,174],"usage":[23],"and":[24,100,106,156,163,192,203],"contamination.":[26],"Existing":[27],"approaches,":[28],"such":[29],"as":[30,55,103,137],"backdoor":[31,197],"watermarking,":[32],"rely":[33],"on":[34,43,121,159,181],"inducing":[35],"detectable":[37],"behavior":[38],"into":[39],"trained":[41,120,180],"model":[42],"part":[45],"distribution.":[49],"However,":[50],"these":[51],"approaches":[52,75],"have":[53],"limitations,":[54],"they":[56],"can":[57,176],"be":[58],"harmful":[59],"to":[60,68,112,124,138,147],"performances":[63],"or":[64],"require":[65],"unpractical":[66],"access":[67,145],"internals.":[71],"Most":[72],"importantly,":[73],"previous":[74],"lack":[76],"guarantee":[77],"against":[78,208],"false":[79],"positives.":[80],"This":[81],"paper":[82],"introduces":[83],"taggants,":[85],"novel":[87],"non-backdoor":[88],"verification":[91],"technique.":[92],"Our":[93,170],"method":[94,207],"uses":[95],"pairs":[96],"out-of-distribution":[98],"samples":[99,127],"random":[101],"labels":[102],"secret":[104],"keys,":[105],"leverages":[107],"clean-label":[108],"targeted":[109],"poisoning":[111],"subtly":[113],"alter":[114],"dataset,":[116],"so":[117],"that":[118,173],"models":[119,165,179],"it":[122],"respond":[123],"key":[126,131],"with":[128,143,166,185],"corresponding":[130],"labels.":[132],"The":[133],"keys":[134],"are":[135],"built":[136],"allow":[139],"statistical":[141],"certificates":[142],"black-box":[144],"only":[146],"model.":[149],"We":[150,199],"validate":[151],"our":[152,206],"approach":[153],"through":[154],"comprehensive":[155],"realistic":[157],"experiments":[158],"ImageNet1k":[160],"using":[161],"ViT":[162],"ResNet":[164],"state-of-the-art":[167],"recipes.":[169],"findings":[171],"demonstrate":[172,200],"taggants":[175],"reliably":[177],"detect":[178],"protected":[183],"high":[186],"confidence,":[187],"without":[188],"compromising":[189],"validation":[190],"accuracy,":[191],"show":[193],"their":[194],"superiority":[195],"over":[196],"watermarking.":[198],"stealthiness":[202],"robustness":[204],"various":[209],"defense":[210],"mechanisms.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-10-20T00:00:00"}