{"id":"https://openalex.org/W7220403231","doi":"https://doi.org/10.48550/arxiv.2610.02418","title":"Mitigating Private Data Leakage in LLMs with Whiteout","display_name":"Mitigating Private Data Leakage in LLMs with Whiteout","publication_year":2026,"publication_date":"2026-10-01","ids":{"openalex":"https://openalex.org/W7220403231","doi":"https://doi.org/10.48550/arxiv.2610.02418"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.02418","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.02418","pdf_url":"https://arxiv.org/pdf/2610.02418","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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/2610.02418","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093876076","display_name":"Anna Yoo Jeong Ha","orcid":"https://orcid.org/0009-0008-5551-7847","observed_orcids":["https://orcid.org/0009-0008-5551-7847"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ha, Anna Yoo Jeong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061419124","display_name":"Ronik Bhaskar","orcid":"https://orcid.org/0009-0002-7524-9292","observed_orcids":["https://orcid.org/0009-0002-7524-9292"]},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhaskar, Ronik","raw_affiliation_strings":["Department of Computer Science , University of Chicago {annaha ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Chicago {annaha ,","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137348758","display_name":"Haitao Zheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng, Haitao","raw_affiliation_strings":["Department of Computer Science , University of Chicago {annaha ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Chicago {annaha ,","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108248360","display_name":"Ben Y. Zhao","orcid":"https://orcid.org/0009-0003-8909-0494","observed_orcids":["https://orcid.org/0009-0003-8909-0494"]},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao, Ben Y.","raw_affiliation_strings":["Department of Computer Science , University of Chicago {annaha ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Chicago {annaha ,","institution_ids":["https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.899399995803833,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.899399995803833,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.09610000252723694,"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/T11045","display_name":"Privacy, Security, and Data Protection","score":0.0010000000474974513,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8109999895095825},{"id":"https://openalex.org/keywords/memorization","display_name":"memorization","score":0.5289999842643738},{"id":"https://openalex.org/keywords/data-obfuscation","display_name":"data obfuscation","score":0.6679999828338623},{"id":"https://openalex.org/keywords/privacy-protection","display_name":"privacy preservation","score":0.5419999957084656},{"id":"https://openalex.org/keywords/machine-unlearning","display_name":"machine unlearning","score":0.8140000104904175},{"id":"https://openalex.org/keywords/jailbreak-attacks","display_name":"jailbreak attacks","score":0.7300000190734863}],"concepts":[{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.6132000088691711},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5684000253677368},{"id":"https://openalex.org/C40305131","wikidata":"https://www.wikidata.org/wiki/Q2616305","display_name":"Obfuscation","level":2,"score":0.5135999917984009},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.47519999742507935},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4381999969482422},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.4074999988079071},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.37560001015663147},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.2587999999523163},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.25459998846054077},{"id":"https://openalex.org/C189326681","wikidata":"https://www.wikidata.org/wiki/Q10294","display_name":"Poverty","level":2,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.02418","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.02418","pdf_url":"https://arxiv.org/pdf/2610.02418","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.02418","doi":"https://doi.org/10.48550/arxiv.2610.02418","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.02418","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:2610.02418","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.02418","pdf_url":"https://arxiv.org/pdf/2610.02418","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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/W7220403231.pdf","grobid_xml":"https://content.openalex.org/works/W7220403231.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2794325560","https://openalex.org/W4322718191","https://openalex.org/W4385374425","https://openalex.org/W4386977575","https://openalex.org/W4387389584","https://openalex.org/W4392223220","https://openalex.org/W4395474395","https://openalex.org/W4405354744","https://openalex.org/W4414448605","https://openalex.org/W4415332740","https://openalex.org/W4416060618","https://openalex.org/W6947991961","https://openalex.org/W7075994024","https://openalex.org/W7125923365","https://openalex.org/W7160638842"],"related_works":["https://openalex.org/W4400703145","https://openalex.org/W7204925876","https://openalex.org/W4417060168","https://openalex.org/W4414850745","https://openalex.org/W4405181291","https://openalex.org/W4412945112","https://openalex.org/W7133218973","https://openalex.org/W4391107696","https://openalex.org/W7147475086","https://openalex.org/W4387355380"],"abstract_inverted_index":{"Modern":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"are":[5,82],"trained":[6],"on":[7,64,119,146,184],"massive,":[8],"largely":[9,62],"unfiltered":[10],"datasets,":[11],"including":[12,127],"content":[13],"scraped":[14],"from":[15,101,165],"nearly":[16],"every":[17],"accessible":[18],"website":[19],"and":[20,29,41,58,79,81,111,125,149,151,176,187],"user":[21],"inputs.":[22],"As":[23],"a":[24,91,128,160,182],"result,":[25],"LLMs":[26,100,121],"often":[27,70],"memorize":[28],"reproduce":[30],"personally":[31],"sensitive":[32],"information":[33,73],"(PSI)":[34],"such":[35,54],"as":[36,55],"birth":[37],"dates,":[38],"phone":[39],"numbers,":[40],"home":[42],"addresses.":[43],"This":[44,87],"leads":[45],"to":[46,85,170],"significant":[47],"privacy":[48],"risks,":[49],"particularly":[50],"for":[51],"high-profile":[52],"individuals":[53],"executives,":[56],"politicians,":[57],"judges.":[59],"Existing":[60],"mitigations":[61],"rely":[63],"machine":[65],"unlearning.":[66],"However,":[67],"these":[68],"methods":[69],"remove":[71],"more":[72],"than":[74],"needed,":[75],"degrade":[76],"model":[77,147],"utility":[78,148],"safety,":[80,150],"highly":[83],"vulnerable":[84],"attacks.":[86],"paper":[88],"presents":[89],"Whiteout,":[90],"practical":[92],"tool":[93],"that,":[94],"upon":[95],"requests":[96],"by":[97,106],"individuals,":[98],"prevents":[99,137],"regurgitating":[102],"their":[103],"genuine":[104],"PSIs,":[105,142],"overwriting":[107],"them":[108],"using":[109],"precise":[110],"carefully":[112],"designed":[113],"obfuscation":[114],"samples.":[115],"We":[116,155],"evaluate":[117],"Whiteout":[118,135,158],"modern":[120],"of":[122,139,163,190],"varying":[123],"sizes":[124],"makers,":[126],"widely-used":[129],"OpenAI":[130],"model.":[131],"Results":[132],"show":[133],"that":[134],"effectively":[136],"disclosure":[138],"the":[140,185],"targeted":[141],"has":[143],"negligible":[144],"impact":[145],"outperforms":[152],"existing":[153],"alternatives.":[154],"also":[156],"test":[157],"against":[159],"wide":[161],"range":[162],"countermeasures,":[164],"black-box":[166],"attacks":[167,173],"like":[168,174],"jailbreaking":[169],"white-box":[171],"adaptive":[172],"relearning":[175],"quantization.":[177],"Finally,":[178],"we":[179],"conclude":[180],"with":[181],"discussion":[183],"security":[186],"ethical":[188],"implications":[189],"Whiteout.":[191]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-06T00:00:00"}