{"id":"https://openalex.org/W4414934331","doi":"https://doi.org/10.48550/arxiv.2510.09655","title":"Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique","display_name":"Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique","publication_year":2025,"publication_date":"2025-10-07","ids":{"openalex":"https://openalex.org/W4414934331","doi":"https://doi.org/10.48550/arxiv.2510.09655"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2510.09655","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.09655","pdf_url":"https://arxiv.org/pdf/2510.09655","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":null,"license_id":null,"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/2510.09655","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005015276","display_name":"Yanming Li","orcid":null,"observed_orcids":[]},"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/I4405258580","display_name":"PETSCRAFT: Concevoir des technologies d'am\u00e9lioration de la vie priv\u00e9e explicables et efficaces","ror":"https://ror.org/00xv6bg25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210126360","https://openalex.org/I4405258580"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Li, Yanming","raw_affiliation_strings":["PETSCRAFT","PETSCRAFT - Concevoir des technologies d'am\u00e9lioration de la vie priv\u00e9e explicables et efficaces (Campus de l'\u00c9cole Polytechnique 91120 Palaiseau - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PETSCRAFT","institution_ids":["https://openalex.org/I4405258580"]},{"raw_affiliation_string":"PETSCRAFT - Concevoir des technologies d'am\u00e9lioration de la vie priv\u00e9e explicables et efficaces (Campus de l'\u00c9cole Polytechnique 91120 Palaiseau - France)","institution_ids":["https://openalex.org/I142476485","https://openalex.org/I4405258580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070235439","display_name":"C\u00e9dric Eichler","orcid":"https://orcid.org/0000-0003-3026-1749","observed_orcids":["https://orcid.org/0000-0003-3026-1749"]},"institutions":[{"id":"https://openalex.org/I201181511","display_name":"\u00c9cole Nationale Sup\u00e9rieure de Techniques Avanc\u00e9es","ror":"https://ror.org/0309cs235","country_code":"FR","type":"education","lineage":["https://openalex.org/I201181511","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4405258580","display_name":"PETSCRAFT: Concevoir des technologies d'am\u00e9lioration de la vie priv\u00e9e explicables et efficaces","ror":"https://ror.org/00xv6bg25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210126360","https://openalex.org/I4405258580"]},{"id":"https://openalex.org/I4405258625","display_name":"\u00c9cole Nationale Sup\u00e9rieure de Techniques Avanc\u00e9es Paris","ror":"https://ror.org/0106ccb15","country_code":"FR","type":"education","lineage":["https://openalex.org/I201181511","https://openalex.org/I4210145102","https://openalex.org/I4405258625"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Eichler, C\u00e9dric","raw_affiliation_strings":["PETSCRAFT","ENSTA - \u00c9cole Nationale Sup\u00e9rieure de Techniques Avanc\u00e9es (828, boulevard des Mar\u00e9chaux 91120 Palaiseau - 2 rue Fran\u00e7ois Verny, 29806 Brest cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PETSCRAFT","institution_ids":["https://openalex.org/I4405258580"]},{"raw_affiliation_string":"ENSTA - \u00c9cole Nationale Sup\u00e9rieure de Techniques Avanc\u00e9es (828, boulevard des Mar\u00e9chaux 91120 Palaiseau - 2 rue Fran\u00e7ois Verny, 29806 Brest cedex 9 - France)","institution_ids":["https://openalex.org/I201181511","https://openalex.org/I4405258625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048401513","display_name":"Nicolas Anciaux","orcid":"https://orcid.org/0009-0003-7537-295X","observed_orcids":["https://orcid.org/0009-0003-7537-295X"]},"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/I4405258580","display_name":"PETSCRAFT: Concevoir des technologies d'am\u00e9lioration de la vie priv\u00e9e explicables et efficaces","ror":"https://ror.org/00xv6bg25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210126360","https://openalex.org/I4405258580"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Anciaux, Nicolas","raw_affiliation_strings":["PETSCRAFT","PETSCRAFT - Concevoir des technologies d'am\u00e9lioration de la vie priv\u00e9e explicables et efficaces (Campus de l'\u00c9cole Polytechnique 91120 Palaiseau - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PETSCRAFT","institution_ids":["https://openalex.org/I4405258580"]},{"raw_affiliation_string":"PETSCRAFT - Concevoir des technologies d'am\u00e9lioration de la vie priv\u00e9e explicables et efficaces (Campus de l'\u00c9cole Polytechnique 91120 Palaiseau - France)","institution_ids":["https://openalex.org/I142476485","https://openalex.org/I4405258580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043315649","display_name":"Alexandra Bensamoun","orcid":null,"observed_orcids":[]},"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/I4405258580","display_name":"PETSCRAFT: Concevoir des technologies d'am\u00e9lioration de la vie priv\u00e9e explicables et efficaces","ror":"https://ror.org/00xv6bg25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210126360","https://openalex.org/I4405258580"]},{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES","FR"],"is_corresponding":false,"raw_author_name":"Bensamoun, Alexandra","raw_affiliation_strings":["UC3M","PETSCRAFT - Concevoir des technologies d'am\u00e9lioration de la vie priv\u00e9e explicables et efficaces (Campus de l'\u00c9cole Polytechnique 91120 Palaiseau - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC3M","institution_ids":["https://openalex.org/I50357001"]},{"raw_affiliation_string":"PETSCRAFT - Concevoir des technologies d'am\u00e9lioration de la vie priv\u00e9e explicables et efficaces (Campus de l'\u00c9cole Polytechnique 91120 Palaiseau - France)","institution_ids":["https://openalex.org/I142476485","https://openalex.org/I4405258580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029953950","display_name":"Lorena Gonz\u00e1lez Manzano","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES","FR"],"is_corresponding":false,"raw_author_name":"Manzano, Lorena Gonzalez","raw_affiliation_strings":["UC3M","Universit\u00e9 Paris-Saclay (B\u00e2timent Br\u00e9guet, 3 Rue Joliot Curie 2e \u00e9t, 91190 Gif-sur-Yvette - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC3M","institution_ids":["https://openalex.org/I50357001"]},{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay (B\u00e2timent Br\u00e9guet, 3 Rue Joliot Curie 2e \u00e9t, 91190 Gif-sur-Yvette - France)","institution_ids":["https://openalex.org/I277688954"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ghozzi, Seifeddine","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ghozzi, Seifeddine","raw_affiliation_strings":["ENSTA","UC3M - Universidad Carlos III de Madrid [Madrid] (Calle Madrid 126, 28903 Getafe, Madrid - Spain)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ENSTA","institution_ids":[]},{"raw_affiliation_string":"UC3M - Universidad Carlos III de Madrid [Madrid] (Calle Madrid 126, 28903 Getafe, Madrid - Spain)","institution_ids":["https://openalex.org/I50357001"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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":0.7202000021934509,"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":0.7202000021934509,"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/T12122","display_name":"Physical Unclonable Functions (PUFs) and Hardware Security","score":0.05590000003576279,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.04989999905228615,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/llm-fine-tuning","display_name":"LLM fine-tuning","score":0.8169999718666077},{"id":"https://openalex.org/keywords/text-watermarking","display_name":"text watermarking","score":0.6079999804496765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.730400025844574},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47999998927116394},{"id":"https://openalex.org/C500551929","wikidata":"https://www.wikidata.org/wiki/Q8819","display_name":"Unicode","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C2779623668","wikidata":"https://www.wikidata.org/wiki/Q7652842","display_name":"SwIPe","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3698999881744385},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3684000074863434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3650999963283539},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35690000653266907},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.34869998693466187},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.2554999887943268},{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.25060001015663147},{"id":"https://openalex.org/C527821871","wikidata":"https://www.wikidata.org/wiki/Q228502","display_name":"Access control","level":2,"score":0.25049999356269836},{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.25029999017715454}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:arXiv.org:2510.09655","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.09655","pdf_url":"https://arxiv.org/pdf/2510.09655","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05293957v2","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-05293957","pdf_url":"https://inria.hal.science/hal-05293957/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"Forty-Third International Conference on Machine Learning (ICML 2026), 2026, S\u00e9oul, France","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-05293957v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-05293957","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"Inria; Insa. 2025","raw_type":"info:eu-repo/semantics/report"},{"id":"pmh:oai:HAL:hal-05293957v3","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05293957","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"https://icml.cc/virtual/2026/poster/66491","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2510.09655","doi":"https://doi.org/10.48550/arxiv.2510.09655","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.09655","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.09655","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.09655","pdf_url":"https://arxiv.org/pdf/2510.09655","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1272900390","display_name":null,"funder_award_id":"PID2023","funder_id":"https://openalex.org/F4320315062","funder_display_name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades"},{"id":"https://openalex.org/G2269199881","display_name":null,"funder_award_id":"PID2023-150310OB-I00","funder_id":"https://openalex.org/F4320315062","funder_display_name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades"},{"id":"https://openalex.org/G4734567674","display_name":"interdisciplinary Project on Privacy","funder_award_id":"ANR-22-PECY-0002","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5209393470","display_name":"Data Science, Artificial Intelligence and Society","funder_award_id":"ANR-17-CONV-0003","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320315062","display_name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","ror":null},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":"https://ror.org/003x0zc53"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414934331.pdf","grobid_xml":"https://content.openalex.org/works/W4414934331.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2535690855","https://openalex.org/W3118781290","https://openalex.org/W3202388704","https://openalex.org/W3212496002","https://openalex.org/W4307079201","https://openalex.org/W4327810158","https://openalex.org/W4383199672","https://openalex.org/W4384648639","https://openalex.org/W4385567130","https://openalex.org/W4387561528","https://openalex.org/W4387857422","https://openalex.org/W4402671286","https://openalex.org/W4402683760","https://openalex.org/W4404330874","https://openalex.org/W4404782423","https://openalex.org/W4410608986","https://openalex.org/W4410609063","https://openalex.org/W4410609172","https://openalex.org/W4411120109","https://openalex.org/W4411337398","https://openalex.org/W4411337932","https://openalex.org/W4412888236","https://openalex.org/W4412944613","https://openalex.org/W4414281281","https://openalex.org/W4416549440"],"related_works":["https://openalex.org/W4414543355","https://openalex.org/W4415981888","https://openalex.org/W7160875822","https://openalex.org/W7221698410","https://openalex.org/W4410608986","https://openalex.org/W4377865883","https://openalex.org/W7161005889","https://openalex.org/W7172481159","https://openalex.org/W4385437823","https://openalex.org/W4415951555"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,71,75,86,135],"system":[3],"for":[4],"marking":[5],"sensitive":[6],"or":[7],"copyrighted":[8],"texts":[9],"to":[10,49,121],"detect":[11],"their":[12],"use":[13],"in":[14],"fine-tuning":[15,140],"large":[16],"language":[17],"models":[18],"under":[19],"black-box":[20],"access":[21],"with":[22,105],"statistical":[23],"guarantees.":[24],"Our":[25],"method":[26],"builds":[27],"digital":[28],"``marks''":[29],"using":[30],"invisible":[31],"Unicode":[32],"characters":[33],"organized":[34],"into":[35],"(``cue'',":[36],"``reply'')":[37],"pairs.":[38],"During":[39],"an":[40],"audit,":[41],"prompts":[42],"containing":[43],"only":[44,106],"``cue''":[45],"fragments":[46],"are":[47],"issued":[48],"trigger":[50],"regurgitation":[51,99],"of":[52,90,138],"the":[53,79,139],"corresponding":[54],"``reply'',":[55],"indicating":[56],"document":[57,104],"usage.":[58],"To":[59],"control":[60],"false":[61,80,94],"positives,":[62],"we":[63,84],"compare":[64],"against":[65],"held-out":[66],"counterfactual":[67],"marks":[68],"and":[69,97,125],"apply":[70],"ranking":[72],"test,":[73],"yielding":[74],"verifiable":[76],"bound":[77],"on":[78],"positive":[81,88,95],"rate.":[82],"Empirically,":[83],"obtain":[85],"true":[87],"rate":[89,96],"96.7%":[91],"at":[92],"0%":[93],"reply":[98],"rates":[100],"exceeding":[101],"28%":[102],"per":[103],"40":[107],"(4%)":[108],"watermarked":[109],"documents.":[110],"The":[111],"approach":[112],"is":[113,134],"minimally":[114],"invasive,":[115],"scalable":[116],"across":[117],"many":[118],"sources,":[119],"robust":[120],"standard":[122],"processing":[123],"pipelines,":[124],"achieves":[126],"high":[127],"detection":[128],"power":[129],"even":[130],"when":[131],"marked":[132],"data":[133],"small":[136],"fraction":[137],"corpus.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-08T00:00:00"}