{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T13:46:39Z","timestamp":1762177599065,"version":"3.37.3"},"reference-count":56,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T00:00:00Z","timestamp":1682553600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T00:00:00Z","timestamp":1682553600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"European Re- search Council","award":["grant agree- ment No. 772834"],"award-info":[{"award-number":["grant agree- ment No. 772834"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2023,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Large machine learning (ML) models with improved predictions have become widely available in the chemical sciences. Unfortunately, these models do not protect the privacy necessary within commercial settings, prohibiting the use of potentially extremely valuable data by others. Encrypting the prediction process can solve this problem by double-blind model evaluation and prohibits the extraction of training or query data. However, contemporary ML models based on fully homomorphic encryption or federated learning are either too expensive for practical use or have to trade higher speed for weaker security. We have implemented secure and computationally feasible encrypted ML models using oblivious transfer enabling and secure predictions of molecular quantum properties across chemical compound space. However, we find that encrypted predictions using kernel ridge regression models are a million times more expensive than without encryption. This demonstrates a dire need for a compact ML model architecture, including molecular representation and kernel matrix size, that minimizes model evaluation costs.<\/jats:p>","DOI":"10.1088\/2632-2153\/acc928","type":"journal-article","created":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T08:50:11Z","timestamp":1682585411000},"page":"025017","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Encrypted machine learning of molecular quantum properties"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9332-4543","authenticated-orcid":true,"given":"Jan","family":"Weinreich","sequence":"first","affiliation":[]},{"given":"Guido","family":"Falk von Rudorff","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7419-0466","authenticated-orcid":true,"given":"O","family":"Anatole von Lilienfeld","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2023,4,27]]},"reference":[{"key":"mlstacc928bib1","article-title":"Source: statista"},{"key":"mlstacc928bib2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41592-021-01205-4","volume":"18","author":"Walsh","year":"2021","journal-title":"Nat. Methods"},{"key":"mlstacc928bib3","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.jhealeco.2016.01.012","volume":"47","author":"DiMasi","year":"2016","journal-title":"J. Health Econ."},{"key":"mlstacc928bib4","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/nrd3078","volume":"9","author":"Paul","year":"2010","journal-title":"Nat. Rev. Drug Discovery"},{"key":"mlstacc928bib5","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.1056\/NEJMp1500848","volume":"372","author":"Avorn","year":"2015","journal-title":"New Engl. J. Med."},{"key":"mlstacc928bib6","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1038\/460208a","volume":"460","author":"Hartung","year":"2009","journal-title":"Nature"},{"key":"mlstacc928bib7","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1186\/s13321-020-00422-x","volume":"12","author":"Morger","year":"2020","journal-title":"J. Cheminf."},{"key":"mlstacc928bib8","doi-asserted-by":"publisher","first-page":"3030","DOI":"10.1021\/es802388s","volume":"43","author":"Choi","year":"2009","journal-title":"Environ. Sci. Technol."},{"key":"mlstacc928bib9","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1111\/risa.13810","volume":"42","author":"Price","year":"2022","journal-title":"Risk Anal."},{"key":"mlstacc928bib10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00204-019-02613-4","volume":"94","author":"Krewski","year":"2020","journal-title":"Arch. Toxicol."},{"key":"mlstacc928bib11","doi-asserted-by":"publisher","first-page":"3320","DOI":"10.1021\/ci5005288","volume":"54","author":"Tetko","year":"2014","journal-title":"J. Chem. Inf. Modeling"},{"year":"2022","author":"MELLODY","key":"mlstacc928bib12"},{"key":"mlstacc928bib13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-021-99269-x","volume":"12","author":"Adnan","year":"2022","journal-title":"Sci. Rep."},{"key":"mlstacc928bib14","first-page":"pp 1273","volume":"vol 54","author":"McMahan","year":"2017","edition":"ed"},{"article-title":"FedJAX: federated learning simulation with JAX","year":"2020","author":"Ro","key":"mlstacc928bib15"},{"article-title":"Federated learning for mobile keyboard prediction","year":"2019","author":"Hard","key":"mlstacc928bib16"},{"article-title":"Capc learning: confidential and private collaborative learning","year":"2021","author":"Choquette-Choo","key":"mlstacc928bib17"},{"key":"mlstacc928bib18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100487","volume":"3","author":"Sav","year":"2022","journal-title":"Patterns"},{"volume":"vol 1","year":"2021","author":"Aggarwal","key":"mlstacc928bib19"},{"key":"mlstacc928bib20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100521","volume":"3","author":"Zhu","year":"2022","journal-title":"Patterns"},{"article-title":"Manipulating sgd with data ordering attacks","year":"2021","author":"Shumailov","key":"mlstacc928bib21"},{"article-title":"Decepticons: corrupted transformers breach privacy in federated learning for language models","year":"2022","author":"Fowl","key":"mlstacc928bib22"},{"article-title":"Fishing for user data in large-batch federated learning via gradient magnification","year":"2022","author":"Wen","key":"mlstacc928bib23"},{"key":"mlstacc928bib24","article-title":"Possible risks of the mellody platform"},{"year":"2022","author":"Fowl","key":"mlstacc928bib25"},{"first-page":"pp 830","year":"2016","author":"Keller","key":"mlstacc928bib26"},{"year":"1998","author":"Vapnik","key":"mlstacc928bib27"},{"year":"2020","author":"Sch\u00fctt","key":"mlstacc928bib28"},{"first-page":"pp 2909","year":"2022","author":"Wang","key":"mlstacc928bib29"},{"first-page":"pp 1322","year":"2015","author":"Fredrikson","key":"mlstacc928bib30"},{"first-page":"pp 3870","year":"2022","author":"Wang","key":"mlstacc928bib31"},{"article-title":"Membership inference attacks against machine learning models","year":"2016","author":"Shokri","key":"mlstacc928bib32"},{"article-title":"Extracting training data from large language models","year":"2020","author":"Carlini","key":"mlstacc928bib33"},{"first-page":"p 160","year":"1982","author":"Yao","key":"mlstacc928bib34"},{"first-page":"p 162","year":"1986","author":"Yao","key":"mlstacc928bib35"},{"first-page":"pp 20","year":"1988","author":"Kilian","key":"mlstacc928bib36"},{"key":"mlstacc928bib37","first-page":"p 187","article-title":"How To Exchange Secrets with Oblivious Transfer","volume":"vol 2005","author":"Rabin","year":"2005","journal-title":"IACR Cryptology ePrint Archive"},{"first-page":"p 169","year":"1978","author":"Rivest","key":"mlstacc928bib38"},{"first-page":"pp 169","year":"2009","author":"Gentry","key":"mlstacc928bib39"},{"key":"mlstacc928bib40","doi-asserted-by":"crossref","DOI":"10.1145\/3372297.3417872","article-title":"Mp-spdz: a versatile framework for multi-party computation","author":"Keller","year":"2020"},{"key":"mlstacc928bib41","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1145\/359340.359342","volume":"21","author":"Rivest","year":"1978","journal-title":"Commun. ACM"},{"key":"mlstacc928bib42","first-page":"pp 884","article-title":"Oblivious transfer","author":"Schoenmakers","year":"2011","edition":"ed"},{"key":"mlstacc928bib43","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.108.058301","volume":"108","author":"Rupp","year":"2012","journal-title":"Phys. Rev. Lett."},{"key":"mlstacc928bib44","doi-asserted-by":"publisher","DOI":"10.1063\/1.5020710","volume":"148","author":"Faber","year":"2018","journal-title":"J. Chem. Phys."},{"key":"mlstacc928bib45","doi-asserted-by":"publisher","DOI":"10.1063\/1.5126701","volume":"152","author":"Christensen","year":"2020","journal-title":"J. Chem. Phys."},{"key":"mlstacc928bib46","doi-asserted-by":"publisher","first-page":"3404","DOI":"10.1021\/ct400195d","volume":"9","author":"Hansen","year":"2013","journal-title":"J. Chem. Theory Comp."},{"key":"mlstacc928bib47","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v34i04.5799","article-title":"Privacy-preserving Gaussian process regression\u2014a modular approach to the application of homomorphic encryption","author":"Fenner","year":"2020"},{"first-page":"pp 143","year":"1999","author":"David Sherrill","key":"mlstacc928bib48"},{"key":"mlstacc928bib49","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ab6ac4","volume":"1","author":"Heinen","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstacc928bib50","doi-asserted-by":"publisher","first-page":"5829","DOI":"10.1063\/1.467146","volume":"100","author":"Sch\u00e4fer","year":"1994","journal-title":"J. Chem. Phys."},{"key":"mlstacc928bib51","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2014.22","volume":"1","author":"Ramakrishnan","year":"2014","journal-title":"Sci. Data"},{"year":"2022","author":"Haim","key":"mlstacc928bib52"},{"first-page":"pp 250","year":"2020","author":"Zhang","key":"mlstacc928bib53"},{"key":"mlstacc928bib54","doi-asserted-by":"publisher","first-page":"2454","DOI":"10.1021\/acs.accounts.2c00220","volume":"55","author":"Seifrid","year":"2022","journal-title":"Acc. Chem. Res."},{"key":"mlstacc928bib55","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem. Inf. Model."},{"year":"2017","author":"Christensen","key":"mlstacc928bib56"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc928","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc928\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc928\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc928\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T08:50:17Z","timestamp":1682585417000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acc928"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,27]]},"references-count":56,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,4,27]]},"published-print":{"date-parts":[[2023,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/acc928","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2023,4,27]]},"assertion":[{"value":"Encrypted machine learning of molecular quantum properties","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2022-12-22","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-03-30","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-04-27","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}