{"id":"https://openalex.org/W7171508104","doi":"https://doi.org/10.1145/3807503.3819470","title":"Quantifying Memorization and Privacy Risks in Genomic Language Models","display_name":"Quantifying Memorization and Privacy Risks in Genomic Language Models","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7171508104","doi":"https://doi.org/10.1145/3807503.3819470"},"language":null,"primary_location":{"id":"doi:10.1145/3807503.3819470","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819470","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3807503.3819470","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5143809490","display_name":"Alexander Nemecek","orcid":"https://orcid.org/0009-0000-2179-4186"},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Nemecek","raw_affiliation_strings":["Case Western Reserve University, Cleveland, Ohio, USA"],"raw_orcid":"https://orcid.org/0009-0000-2179-4186","affiliations":[{"raw_affiliation_string":"Case Western Reserve University, Cleveland, Ohio, USA","institution_ids":["https://openalex.org/I58956616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143837834","display_name":"Wenbiao Li","orcid":"https://orcid.org/0009-0003-7651-696X"},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenbiao Li","raw_affiliation_strings":["Case Western Reserve University, Cleveland, Ohio, USA"],"raw_orcid":"https://orcid.org/0009-0003-7651-696X","affiliations":[{"raw_affiliation_string":"Case Western Reserve University, Cleveland, Ohio, USA","institution_ids":["https://openalex.org/I58956616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055458864","display_name":"Xiaoqian Jiang","orcid":"https://orcid.org/0000-0001-9933-2205"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoqian Jiang","raw_affiliation_strings":["The University of Texas Health Science Center at Houston, Houston, Texas, USA"],"raw_orcid":"https://orcid.org/0000-0001-9933-2205","affiliations":[{"raw_affiliation_string":"The University of Texas Health Science Center at Houston, Houston, Texas, USA","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034878799","display_name":"Jaideep Vaidya","orcid":"https://orcid.org/0000-0002-7420-6947"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaideep Vaidya","raw_affiliation_strings":["Rutgers University, Newark, New Jersey, USA"],"raw_orcid":"https://orcid.org/0000-0002-7420-6947","affiliations":[{"raw_affiliation_string":"Rutgers University, Newark, New Jersey, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028326739","display_name":"Erman Ayday","orcid":"https://orcid.org/0000-0003-3383-1081"},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erman Ayday","raw_affiliation_strings":["Case Western Reserve University, Cleveland, Ohio, USA"],"raw_orcid":"https://orcid.org/0000-0003-3383-1081","affiliations":[{"raw_affiliation_string":"Case Western Reserve University, Cleveland, Ohio, USA","institution_ids":["https://openalex.org/I58956616"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.5630000233650208},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.36329999566078186},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3215000033378601},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.31380000710487366},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.30570000410079956},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.2849000096321106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6261000037193298},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.5630000233650208},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4456000030040741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4002000093460083},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2847999930381775},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.28189998865127563},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2635999917984009}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3807503.3819470","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819470","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3807503.3819470","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3807503.3819470","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1980132682","https://openalex.org/W1987521207","https://openalex.org/W2002458933","https://openalex.org/W2040228409","https://openalex.org/W2051267297","https://openalex.org/W2134153749","https://openalex.org/W2147555013","https://openalex.org/W2153283265","https://openalex.org/W2168610667","https://openalex.org/W2535690855","https://openalex.org/W2794421626","https://openalex.org/W2795435272","https://openalex.org/W2895917461","https://openalex.org/W3037882675","https://openalex.org/W3043806031","https://openalex.org/W3138815606","https://openalex.org/W3159312600","https://openalex.org/W3177765786","https://openalex.org/W4288057780","https://openalex.org/W4316339774","https://openalex.org/W4392289673","https://openalex.org/W4399042930","https://openalex.org/W4404349982","https://openalex.org/W7133235585","https://openalex.org/W7133359708"],"related_works":[],"abstract_inverted_index":{"Genomic":[0],"language":[1,67],"models":[2,30],"(GLMs)":[3],"have":[4],"emerged":[5],"as":[6,28,86,234],"powerful":[7],"tools":[8],"for":[9,73,230,238],"learning":[10],"representations":[11],"of":[12,62,165,204,224],"DNA":[13],"sequences,":[14],"enabling":[15],"advances":[16],"in":[17,65,76,110],"variant":[18],"prediction,":[19],"regulatory":[20,57],"element":[21],"identification,":[22],"and":[23,56,94,125,158,168,189,200,209],"cross-task":[24],"transfer":[25],"learning.":[26],"However,":[27],"these":[29,74],"are":[31,129],"increasingly":[32],"trained":[33],"or":[34],"fine-tuned":[35],"on":[36],"sensitive":[37],"genomic":[38,78,160,239],"cohorts,":[39],"they":[40],"risk":[41,117,141],"memorizing":[42],"specific":[43],"sequences":[44,150],"from":[45],"their":[46],"training":[47,169,210],"data,":[48],"raising":[49],"serious":[50],"concerns":[51],"around":[52],"privacy,":[53],"data":[54,81],"leakage,":[55],"compliance.":[58],"Despite":[59],"growing":[60],"awareness":[61],"memorization":[63,108,140,190,199,205,225],"risks":[64,75,109],"general-purpose":[66],"models,":[68],"little":[69],"systematic":[70],"evaluation":[71,103,134],"exists":[72],"the":[77,182,202,221,228],"domain,":[79],"where":[80],"exhibit":[82,197],"unique":[83],"properties":[84],"such":[85],"a":[87,99,132,138,235],"fixed":[88],"nucleotide":[89],"alphabet,":[90],"strong":[91],"biological":[92],"structure,":[93],"individual":[95],"identifiability.":[96],"We":[97,173],"present":[98],"comprehensive,":[100],"multi-vector":[101,231],"privacy":[102,232],"framework":[104,176],"designed":[105],"to":[106],"quantify":[107],"GLMs.":[111],"Our":[112,192],"approach":[113],"integrates":[114],"three":[115],"complementary":[116],"assessment":[118],"methodologies:":[119],"perplexity-based":[120],"detection,":[121],"canary":[122,149],"sequence":[123,185],"extraction,":[124],"membership":[126],"inference.":[127],"These":[128,212],"combined":[130],"into":[131,155],"unified":[133],"pipeline":[135],"that":[136,195,201,215],"produces":[137],"worst-case":[139],"score.":[142],"To":[143],"enable":[144],"controlled":[145],"evaluation,":[146],"we":[147],"plant":[148],"at":[151,246],"varying":[152],"repetition":[153,167],"rates":[154],"both":[156],"synthetic":[157],"real":[159],"datasets,":[161],"allowing":[162],"precise":[163],"quantification":[164],"how":[166],"dynamics":[170],"influence":[171],"memorization.":[172],"evaluate":[174],"our":[175],"across":[177,207],"multiple":[178],"GLM":[179],"architectures,":[180],"examining":[181],"relationship":[183],"between":[184],"repetition,":[186],"model":[187],"capacity,":[188],"risk.":[191],"results":[193],"establish":[194],"GLMs":[196],"measurable":[198],"degree":[203],"varies":[206],"architectures":[208],"regimes.":[211],"findings":[213],"reveal":[214],"no":[216],"single":[217],"attack":[218],"vector":[219],"captures":[220],"full":[222],"scope":[223],"risk,":[226],"underscoring":[227],"need":[229],"auditing":[233],"standard":[236],"practice":[237],"AI":[240],"systems.":[241],"All":[242],"code":[243],"is":[244],"available":[245],"https://github.com/ANCP2021/GLM-Memorization.":[247]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2026-07-29T00:00:00"}