-
EP4136559
European procedure
- EP About this file
- EP Legal status
- EP Federated register
- EP Event history
- EP Citations
- EP Patent family
- EP All documents
Extract from the Register of European Patents
EP About this file: EP4136559
| EP4136559 - SYSTEM AND METHOD FOR PRIVACY-PRESERVING DISTRIBUTED TRAINING OF MACHINE LEARNING MODELS ON DISTRIBUTED DATASETS [Right-click to bookmark this link] | Status | No opposition filed within time limit Status updated on 16.05.2025 Database last updated on 21.03.2026 | |
| Former | The patent has been granted Status updated on 07.06.2024 | ||
| Former | Grant of patent is intended Status updated on 22.05.2024 | ||
| Former | Request for examination was made Status updated on 20.01.2023 | ||
| Former | The international publication has been made Status updated on 12.11.2021 | ||
| Former | unknown Status updated on 20.05.2020 | Most recent event Tooltip | 06.02.2026 | Lapse of the patent in a contracting state New state(s): MC | published on 11.03.2026 [2026/11] | Applicant(s) | For all designated states ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE (EPFL) EPFL-TTO EPFL Innovation Park J 1015 Lausanne / CH | [2023/08] | Inventor(s) | 01 /
FROELICHER, David 1018 Lausanne / CH | 02 /
TRONCOSO-PASTORIZA, Juan Ramon 1004 Lausanne / CH | 03 /
PYRGELIS, Apostolos 1053 Bretigny-sur-Morrens / CH | 04 /
SAV, Sinem 1004 Lausanne / CH | 05 /
GOMES DE SÁ E SOUSA, Joao 1020 Renens / CH | 06 /
HUBAUX, Jean-Pierre 1025 St-Sulpice VD / CH | 07 /
BOSSUAT, Jean-Philippe 1007 Lausanne / CH | [2023/08] | Representative(s) | Bittner, Peter, et al Peter Bittner und Partner Herrenwiesenweg 2 69207 Sandhausen / DE | [2023/08] | Application number, filing date | 20725150.5 | 08.05.2020 | [2023/08] | WO2020EP62810 | Filing language | EN | Procedural language | EN | Publication | Type: | A1 Application with search report | No.: | WO2021223873 | Date: | 11.11.2021 | Language: | EN | [2021/45] | Type: | A1 Application with search report | No.: | EP4136559 | Date: | 22.02.2023 | Language: | EN | The application published by WIPO in one of the EPO official languages on 11.11.2021 takes the place of the publication of the European patent application. | [2023/08] | Type: | B1 Patent specification | No.: | EP4136559 | Date: | 10.07.2024 | Language: | EN | [2024/28] | Search report(s) | International search report - published on: | EP | 11.11.2021 | Classification | IPC: | G06F21/62, G06N3/04, G06F7/544, G06N3/045, G06N3/08, G06N20/00, H04L9/00 | [2024/23] | CPC: |
G06F21/6245 (EP);
H04L9/008 (EP,US);
G06F7/544 (EP);
G06N20/00 (EP);
G06N3/045 (EP);
G06N3/0499 (EP);
G06N3/08 (EP);
G06N3/09 (EP);
G06N3/098 (EP,US);
G06F2207/4824 (EP)
(-)
|
| Former IPC [2023/08] | G06F21/62, G06N3/04 | Designated contracting states | AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LI, LT, LU, LV, MC, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR [2023/08]
| Extension states | BA | Not yet paid | ME | Not yet paid | Validation states | KH | Not yet paid | MA | Not yet paid | MD | Not yet paid | TN | Not yet paid | Title | German: | SYSTEM UND VERFAHREN FÜR DATENSCHUTZBEWAHRENDES VERTEILTES TRAINING VON MASCHINENLERNMODELLEN AUF VERTEILTEN DATENSÄTZEN | [2023/08] | English: | SYSTEM AND METHOD FOR PRIVACY-PRESERVING DISTRIBUTED TRAINING OF MACHINE LEARNING MODELS ON DISTRIBUTED DATASETS | [2023/08] | French: | SYSTÈME ET PROCÉDÉ POUR L'APPRENTISSAGE DISTRIBUÉ PRÉSERVANT LA CONFIDENTIALITÉ DE MODÈLES D'APPRENTISSAGE MACHINE SUR DES ENSEMBLES DE DONNÉES DISTRIBUÉS | [2023/08] | Entry into regional phase | 13.11.2022 | National basic fee paid | 13.11.2022 | Designation fee(s) paid | 13.11.2022 | Examination fee paid | Examination procedure | 13.11.2022 | Examination requested [2023/08] | 13.11.2022 | Date on which the examining division has become responsible | 17.03.2023 | Amendment by applicant (claims and/or description) | 23.05.2024 | Communication of intention to grant the patent | 03.06.2024 | Fee for grant paid | 03.06.2024 | Fee for publishing/printing paid | 03.06.2024 | Receipt of the translation of the claim(s) | Opposition(s) | 11.04.2025 | No opposition filed within time limit [2025/25] | Fees paid | Renewal fee | 14.11.2022 | Renewal fee patent year 03 | 17.03.2023 | Renewal fee patent year 04 | 14.05.2024 | Renewal fee patent year 05 |
| Opt-out from the exclusive Tooltip competence of the Unified Patent Court | See the Register of the Unified Patent Court for opt-out data | ||
| Responsibility for the accuracy, completeness or quality of the data displayed under the link provided lies entirely with the Unified Patent Court. | Lapses during opposition Tooltip | CZ | 10.07.2024 | HR | 10.07.2024 | MC | 10.07.2024 | PL | 10.07.2024 | SK | 10.07.2024 | SM | 10.07.2024 | NO | 10.10.2024 | RS | 10.10.2024 | GR | 11.10.2024 | IS | 10.11.2024 | [2026/11] |
| Former [2025/23] | CZ | 10.07.2024 | |
| HR | 10.07.2024 | ||
| PL | 10.07.2024 | ||
| SK | 10.07.2024 | ||
| SM | 10.07.2024 | ||
| NO | 10.10.2024 | ||
| RS | 10.10.2024 | ||
| GR | 11.10.2024 | ||
| IS | 10.11.2024 | ||
| Former [2025/21] | HR | 10.07.2024 | |
| PL | 10.07.2024 | ||
| SM | 10.07.2024 | ||
| NO | 10.10.2024 | ||
| RS | 10.10.2024 | ||
| GR | 11.10.2024 | ||
| IS | 10.11.2024 | ||
| Former [2025/10] | HR | 10.07.2024 | |
| PL | 10.07.2024 | ||
| NO | 10.10.2024 | ||
| RS | 10.10.2024 | ||
| GR | 11.10.2024 | ||
| IS | 10.11.2024 | ||
| Former [2025/09] | PL | 10.07.2024 | |
| NO | 10.10.2024 | ||
| GR | 11.10.2024 | ||
| IS | 10.11.2024 | ||
| Former [2025/08] | PL | 10.07.2024 | |
| NO | 10.10.2024 | ||
| GR | 11.10.2024 | Cited in | International search | [I] US2020125739 (VERMA DINESH C et al.) | [I] LIU CHANGCHANG ET AL: "Secure Model Fusion for Distributed Learning Using Partial Homomorphic Encryption", 25 April 2019, ADVANCES IN DATABASES AND INFORMATION SYSTEMS; [LECTURE NOTES IN COMPUTER SCIENCE; LECT.NOTES COMPUTER], SPRINGER INTERNATIONAL PUBLISHING, CHAM, PAGE(S) 154 - 179, ISBN: 978-3-319-10403-4, XP047507043 DOI: http://dx.doi.org/10.1007/978-3-030-17277-0_9 | [T] SINEM SAV ET AL: "POSEIDON:Privacy-Preserving Federated Neural Network Learning", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 1 September 2020 (2020-09-01), XP081753268 | by applicant | D. WOLINSKYH. CORRIGAN-GIBBSB. FORDA. JOHNSON, SCALABLE ANONYMOUS GROUP COMMUNICATION IN THE ANYTRUST MODEL., 2012 | W. ZHENGR. A. POPAJ. E. GONZALEZI. STOICA: "Helen: Maliciously secure coopetitive learning for linear models", IEEE SYMPOSIUM ON SECURITY AND PRIVACY (S&P, 2019 | P. MOHASSELY. ZHANG. SECUREML: "A system for scalable privacy-preserving machine learning", 2017 IEEE SYMPOSIUM ON SECURITY AND PRIVACY (SP, May 2017 (2017-05-01), pages 19 - 38 | P. MOHASSELP. RINDAL: "Aby 3: a mixed protocol framework for machine learning", ACM CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY (CCS, 2018 | S. WAGHD. GUPTAN. CHANDRAN: "SecureNN: 3-party secure computation for neural network training", PRIVACY ENHANCING TECHNOLOGIES (PETS, 2019 | J. DEANS. GHEMAWAT: "MapReduce: simplified data processing on large clusters", COMMUNICATIONS OF THE ACM, 2008 | J. A. NELDERR. W. M. WEDDERBURN: "Generalized linear models", JOURNAL OF THE ROYAL STATISTICAL SOCIETY, 1972 | A. KUMARJ. NAUGHTONJ. M. PATEL: "Learning generalized linear models over normalized data", ACM INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA (SIGMOD, 2015 | DU, SIMON S. ET AL.: "Gradient descent provably optimizes over-parameterized neural networks", ARXIV, 2018 | T. ZHANG: "Solving large scale linear prediction problems using stochastic gradient descent algorithms", INTERNATIONAL CONFERENCE ON MACHINE LEARNING (ICML, 2004 | I. GOODFELLOWY. BENGIOA. COURVILLE: "Deep Learning", 2016, MIT PRESS | P. TOULISE. AIROLDIJ. RENNIE: "Statistical analysis of stochastic gradient methods for generalized linear models", INTERNATIONAL CONFERENCE ON MACHINE LEARNING (ICML, 2014 | J. WANGG. JOSHI: "Cooperative SGD: A unified framework for the design and analysis of communication-efficient SGD algorithms", CORR, 2018 | Y. NESTEROV: "Smooth minimization of non-smooth functions", MATHEMATICAL PROGRAMMING, vol. 103, no. 1, 2005, pages 127 - 152, XP019355754, DOI: 10.1007/s10107-004-0552-5 DOI: http://dx.doi.org/10.1007/s10107-004-0552-5 | C. MOUCHETJ. R. TRONCOSO-PASTORIZAJ. P. HUBAUX: "Multiparty homomorphic encryption: From theory to practice", TECHNICAL REPORT, vol. 816, 2019, Retrieved from the Internet | J. H. CHEONA. KIMM. KIMY. SONG: "Homomorphic encryption for arithmetic of approximate numbers", SPRINGER INTERNATIONAL CONFERENCE ON THE THEORY AND APPLICATION OF CRYPTOLOGY AND INFORMATION SECURITY (ASIACRYPT, 2017 | V. LYUBASHEVSKYC. PEIKERTO. REGEV: "On ideal lattices and learning with errors over rings", SPRINGER ANNUAL INTERNATIONAL CONFERENCE ON THE THEORY AND APPLICATIONS OF CRYPTOGRAPHIC TECHNIQUES (EUROCRYPT, 2010 | LATTIGO: A LIBRARY FOR LATTICE-BASED HOMOMORPHIC ENCRYPTION IN GO, 14 February 2019 (2019-02-14), Retrieved from the Internet | A. KIMY. SONGM. KIMK. LEEJ. H. CHEON: "Logistic regression model training based on the approximate homomorphic encryption", BMC 786 MEDICAL GENOMICS, 2018 | S. HALEVIV. SHOUP: "Annual International Cryptology Conference (CRYPTO", 2014, SPRINGER, article "Algorithms in helib" | K. HAND. KI: "Better bootstrapping for approximate homomorphic encryption", CRYPTOLOGY EPRINT ARCHIVE, REPORT 2019/688, 2019, Retrieved from the Internet | M. ALBRECHTM. CHASEH. CHENJ. DINGS. GOLDWASSERS. GORBUNOVS. HALEVIJ. HOFFSTEINK. LAINEK. LAUTER: "Homomorphic encryption security standard", TECHNICAL REPORT, November 2018 (2018-11-01), Retrieved from the Internet |