{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:59:13Z","timestamp":1785340753239,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,30]]},"DOI":"10.1145\/3807503.3819470","type":"proceedings-article","created":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T02:55:27Z","timestamp":1785293727000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Quantifying Memorization and Privacy Risks in Genomic Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2179-4186","authenticated-orcid":false,"given":"Alexander","family":"Nemecek","sequence":"first","affiliation":[{"name":"Case Western Reserve University, Cleveland, Ohio, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7651-696X","authenticated-orcid":false,"given":"Wenbiao","family":"Li","sequence":"additional","affiliation":[{"name":"Case Western Reserve University, Cleveland, Ohio, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9933-2205","authenticated-orcid":false,"given":"Xiaoqian","family":"Jiang","sequence":"additional","affiliation":[{"name":"The University of Texas Health Science Center at Houston, Houston, Texas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7420-6947","authenticated-orcid":false,"given":"Jaideep","family":"Vaidya","sequence":"additional","affiliation":[{"name":"Rutgers University, Newark, New Jersey, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3383-1081","authenticated-orcid":false,"given":"Erman","family":"Ayday","sequence":"additional","affiliation":[{"name":"Case Western Reserve University, Cleveland, Ohio, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,28]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Nour Almadhoun Erman Ayday and \u00d6zg\u00fcr Ulusoy. 2020. Inference Attacks Against Differentially Private Query Results from Genomic Datasets Including Dependent Tuples. Bioinformatics 36 Suppl_1 (2020) i136\u2013i145.","DOI":"10.1093\/bioinformatics\/btaa475"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Kerem Ayoz Erman Ayday and A.\u00a0Ercument Cicek. 2021. Genome Reconstruction Attacks Against Genomic Data-Sharing Beacons. Proceedings on Privacy Enhancing Technologies (PoPETs) 2021 3 (2021) 28\u201348.","DOI":"10.2478\/popets-2021-0036"},{"key":"e_1_3_3_2_4_2","unstructured":"Alessandro Belfiore Jonathan Passerat-Palmbach and Dmitrii Usynin. 2025. Biologically-Informed Hybrid Membership Inference Attacks on Generative Genomic Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2511.07503 (2025)."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Frederick\u00a0R Blattner Guy Plunkett\u00a0III Craig\u00a0A Bloch Nicole\u00a0T Perna Valerie Burland Monica Riley Julio Collado-Vides Jeremy\u00a0D Glasner Christopher\u00a0K Rode George\u00a0F Mayhew et\u00a0al. 1997. The complete genome sequence of Escherichia coli K-12. science 277 5331 (1997) 1453\u20131462.","DOI":"10.1126\/science.277.5331.1453"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Luca Bonomi Yingxiang Huang and Lucila Ohno-Machado. 2020. Privacy Challenges and Research Opportunities for Genomic Data Sharing. Nature Genetics 52 7 (2020) 646\u2013654.","DOI":"10.1038\/s41588-020-0651-0"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP46214.2022.9833649"},{"key":"e_1_3_3_2_8_2","volume-title":"Proceedings of the Eleventh International Conference on Learning Representations (ICLR)","author":"Carlini Nicholas","year":"2023","unstructured":"Nicholas Carlini, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Florian Tram\u00e8r, and Chiyuan Zhang. 2023. Quantifying Memorization Across Neural Language Models. In Proceedings of the Eleventh International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_9_2","first-page":"267","volume-title":"28th USENIX Security Symposium (USENIX Security 19)","author":"Carlini Nicholas","year":"2019","unstructured":"Nicholas Carlini, Chang Liu, \u00dalfar Erlingsson, Jernej Kos, and Dawn Song. 2019. The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks. In 28th USENIX Security Symposium (USENIX Security 19). 267\u2013284."},{"key":"e_1_3_3_2_10_2","first-page":"2633","volume-title":"30th USENIX Security Symposium (USENIX Security 21)","author":"Carlini Nicholas","year":"2021","unstructured":"Nicholas Carlini, Florian Tram\u00e8r, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom\u00a0B. Brown, Dawn Song, \u00dalfar Erlingsson, Alina Oprea, and Colin Raffel. 2021. Extracting Training Data from Large Language Models. In 30th USENIX Security Symposium (USENIX Security 21). 2633\u20132650."},{"key":"e_1_3_3_2_11_2","first-page":"26","volume-title":"Pacific Symposium on Biocomputing (PSB)","author":"Chen Junjie","year":"2021","unstructured":"Junjie Chen, Xiaoqian Wang, and Bin Peng. 2021. Differential Privacy Protection Against Membership Inference Attack on Machine Learning for Genomic Data. In Pacific Symposium on Biocomputing (PSB). 26\u201337."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Hugo Dalla-Torre Liam Gonzalez Javier Mendoza-Revilla Nicolas\u00a0Lopez Carranza Adam Grzywaczewski Florian Ober et\u00a0al. 2023. The Nucleotide Transformer: Building and Evaluating Robust Foundation Models for Human Genomics. bioRxiv (2023).","DOI":"10.1101\/2023.01.11.523679"},{"key":"e_1_3_3_2_13_2","volume-title":"Conference on Language Modeling (COLM)","author":"Duan Michael","year":"2024","unstructured":"Michael Duan, Anshuman Suri, Niloofar Mireshghallah, Sewon Min, Weijia Shi, Luke Zettlemoyer, Yulia Tsvetkov, Yejin Choi, David Evans, and Hannaneh Hajishirzi. 2024. Do Membership Inference Attacks Work on Large Language Models?. In Conference on Language Modeling (COLM)."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Stacia\u00a0R Engel Fred\u00a0S Dietrich Dianna\u00a0G Fisk Gail Binkley Rama Balakrishnan Maria\u00a0C Costanzo Selina\u00a0S Dwight Benjamin\u00a0C Hitz Kalpana Karra Robert\u00a0S Nash et\u00a0al. 2014. The reference genome sequence of Saccharomyces cerevisiae: then and now. G3: Genes Genomes Genetics 4 3 (2014) 389\u2013398.","DOI":"10.1534\/g3.113.008995"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Yaniv Erlich and Arvind Narayanan. 2014. Routes for Breaching and Protecting Genetic Privacy. Nature Reviews Genetics 15 6 (2014) 409\u2013421.","DOI":"10.1038\/nrg3723"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Yaniv Erlich Tal Shor Shai Carmi and Itsik Pe\u2019er. 2018. Identity Inference of Genomic Data Using Long-Range Familial Searches. Science 362 6415 (2018) 690\u2013694.","DOI":"10.1126\/science.aau4832"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Md\u00a0Humaion\u00a0Kabir Faysal Juan Acosta Harsh Shukla Dhruvil Trivedi Laila Khatun and Shameer Kanwal. 2024. Assessing Privacy Vulnerabilities in Genetic Data Sets. JMIR Bioinformatics and Biotechnology 5 (2024) e54332.","DOI":"10.2196\/54332"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813677"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Andr\u00e9 Goffeau Bart\u00a0G Barrell Howard Bussey Ronald\u00a0W Davis Bernard Dujon Heinz Feldmann Francis Galibert J\u00f6rg\u00a0D Hoheisel Claude Jacq Michael Johnston et\u00a0al. 1996. Life with 6000 genes. Science 274 5287 (1996) 546\u2013567.","DOI":"10.1126\/science.274.5287.546"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Melissa Gymrek Amy\u00a0L. McGuire David Golan Eran Halperin and Yaniv Erlich. 2013. Identifying Personal Genomes by Surname Inference. Science 339 6117 (2013) 321\u2013324.","DOI":"10.1126\/science.1229566"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Nils Homer Szabolcs Szelinger Margot Redman David Duggan Waibhav Tembe Jill Muehling John\u00a0V. Pearson Dietrich\u00a0A. Stephan Stanley\u00a0F. Nelson and David\u00a0W. Craig. 2008. Resolving Individuals Contributing Trace Amounts of DNA to Highly Complex Mixtures Using High-Density SNP Genotyping Microarrays. PLoS Genetics 4 8 (2008) e1000167.","DOI":"10.1371\/journal.pgen.1000167"},{"key":"e_1_3_3_2_22_2","unstructured":"Edward\u00a0J Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Liang Wang Weizhu Chen et\u00a0al. 2022. Lora: Low-rank adaptation of large language models. Iclr 1 2 (2022) 3."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Hongsheng Hu Zoran Salcic Lichao Sun Gillian Dobbie Philip\u00a0S. Yu and Xuyun Zhang. 2022. Membership Inference Attacks on Machine Learning: A Survey. Comput. Surveys 54 11s (2022) 1\u201337.","DOI":"10.1145\/3523273"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/2508859.2516707"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.6028\/NIST.SP.800-30r1"},{"key":"e_1_3_3_2_26_2","first-page":"10697","volume-title":"Proceedings of the 39th International Conference on Machine Learning (ICML)","author":"Kandpal Nikhil","year":"2022","unstructured":"Nikhil Kandpal, Eric Wallace, and Colin Raffel. 2022. Deduplicating Training Data Mitigates Privacy Risks in Language Models. In Proceedings of the 39th International Conference on Machine Learning (ICML). PMLR, 10697\u201310707."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Dmitrii Kolobkov Satyarth Mishra\u00a0Sharma Aleksandr Medvedev Mikhail Lebedev Egor Kosaretskiy and Ruslan Vakhitov. 2024. Efficacy of Federated Learning on Genomic Data: A Study on the UK Biobank and the 1000 Genomes Project. Frontiers in Big Data 7 (2024) 1266031.","DOI":"10.3389\/fdata.2024.1266031"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.577"},{"key":"e_1_3_3_2_29_2","volume-title":"Proceedings of the Tenth International Conference on Learning Representations (ICLR)","author":"Li Xuechen","year":"2022","unstructured":"Xuechen Li, Florian Tram\u00e8r, Percy Liang, and Tatsunori Hashimoto. 2022. Large Language Models Can Be Strong Differentially Private Learners. In Proceedings of the Tenth International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_30_2","first-page":"4579","volume-title":"31st USENIX Security Symposium (USENIX Security 22)","author":"Mehnaz Shagufta","year":"2022","unstructured":"Shagufta Mehnaz, Sayanton\u00a0V. Dibbo, Ehsanul Kabir, Ninghui Li, and Elisa Bertino. 2022. Are Your Sensitive Attributes Private? Novel Model Inversion Attribute Inference Attacks on Classification Models. In 31st USENIX Security Symposium (USENIX Security 22). 4579\u20134596."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Muhammad Naveed Erman Ayday Ellen\u00a0W. Clayton Jacques Fellay Carl\u00a0A. Gunter Jean-Pierre Hubaux Bradley\u00a0A. Malin and XiaoFeng Wang. 2015. Privacy in the Genomic Era. Comput. Surveys 48 1 (2015) 1\u201344.","DOI":"10.1145\/2767007"},{"key":"e_1_3_3_2_32_2","unstructured":"NCBI RefSeq. 2026. Escherichia coli str. K-12 substr. MG1655 complete genome (ASM584v2 RefSeq assembly GCF_000005845.2). https:\/\/www.ncbi.nlm.nih.gov\/datasets\/genome\/GCF_000005845.2\/. Accessed: 2026-03-04."},{"key":"e_1_3_3_2_33_2","unstructured":"NCBI RefSeq. 2026. Saccharomyces cerevisiae S288C reference genome R64 (RefSeq assembly GCF_000146045.2). https:\/\/www.ncbi.nlm.nih.gov\/datasets\/genome\/GCF_000146045.2\/. Accessed: 2026-03-04."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"crossref","unstructured":"Alexander Nemecek Zebin Yun Zahra Rahmani Yaniv Harel Vipin Chaudhary Mahmood Sharif and Erman Ayday. 2025. Exploring Membership Inference Vulnerabilities in Clinical Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.18674 (2025).","DOI":"10.1109\/TPS-ISA67132.2025.00061"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Eric Nguyen Michael Poli Matthew\u00a0G. Durrant Armin\u00a0W. Thomas Brian Kang Jeremy Sullivan et\u00a0al. 2024. Sequence Modeling and Design from Molecular to Genome Scale with Evo. Science 386 6723 (2024) ado9336.","DOI":"10.1126\/science.ado9336"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1872"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"e_1_3_3_2_38_2","unstructured":"Hao Wu and Yang Cao. 2025. Membership Inference Attacks on Large-Scale Models: A Survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.19338 (2025)."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2018.00027"},{"key":"e_1_3_3_2_40_2","volume-title":"Proceedings of the Twelfth International Conference on Learning Representations (ICLR)","author":"Zhou Zhihan","year":"2024","unstructured":"Zhihan Zhou, Yanrong Ji, Weijian Li, Pratik Dutta, Ramana\u00a0V. Davuluri, and Han Liu. 2024. DNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genome. In Proceedings of the Twelfth International Conference on Learning Representations (ICLR)."}],"event":{"name":"BCB '26: 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","location":"Rende (CS) Italy","acronym":"BCB '26","sponsor":["SIGBio ACM Special Interest Group on Bioinformatics"]},"container-title":["Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3807503.3819470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:12:00Z","timestamp":1785337920000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3807503.3819470"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":39,"alternative-id":["10.1145\/3807503.3819470","10.1145\/3807503"],"URL":"https:\/\/doi.org\/10.1145\/3807503.3819470","relation":{},"subject":[],"published":{"date-parts":[[2026,6,30]]},"assertion":[{"value":"2026-07-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}