MACHINE LEARNING MODEL SCORE OBFUSCATION USING STEP-FUNCTION, POSITION-DEPENDENT NOISE

(19)

(11)

EP 3 963 489 B8

(12)	CORRECTED EUROPEAN PATENT SPECIFICATION
	Note: Bibliography reflects the latest situation

(15)	Correction information:
	Corrected version no 1 (W1 B1)

(48)	Corrigendum issued on:
	06.11.2024 Bulletin 2024/45

(45)	Mention of the grant of the patent:
	02.10.2024 Bulletin 2024/40

(21)	Application number: 20727021.6

(22)	Date of filing: 28.04.2020

(51)

International Patent Classification (IPC):

G06F 21/56^(2013.01)
G06N 3/044^(2023.01)
G06N 3/049^(2023.01)
G06N 5/01^(2023.01)
G06N 7/01^(2023.01)

H04L 9/40^(2022.01)
G06N 3/045^(2023.01)
G06N 3/088^(2023.01)
G06N 20/10^(2019.01)
G06N 20/20^(2019.01)

(52)	Cooperative Patent Classification (CPC):
	G06F 21/563; H04L 63/1441; H04L 63/145; G06F 21/562; G06N 20/20; G06N 20/10; G06N 3/049; G06N 3/088; G06N 5/01; G06N 7/01; G06N 3/044; G06N 3/045

(86)	International application number:
	PCT/US2020/030247

(87)	International publication number:
	WO 2020/223222 (05.11.2020 Gazette 2020/45)

(54)

MACHINE LEARNING MODEL SCORE OBFUSCATION USING STEP-FUNCTION, POSITION-DEPENDENT NOISE

MASCHINENLERNMODELLWERTVERSCHLEIERUNG UNTER VERWENDUNG VON SCHRITTFUNKTIONALEM POSITIONSABHÄNGIGEM RAUSCHEN

OBSCURCISSEMENT DE SCORE DE MODÈLE D'APPRENTISSAGE AUTOMATIQUE UTILISANT DU BRUIT À FONCTION EN ESCALIER DÉPENDANT DE LA POSITION

(84)	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

(30)

Priority:

30.04.2019 US 201916399665
30.04.2019 US 201916399718
30.04.2019 US 201916399701
30.04.2019 US 201916399735
30.04.2019 US 201916399677

(43)	Date of publication of application:
	09.03.2022 Bulletin 2022/10

(73)	Proprietor: Cylance Inc.
	Irving, TX 75039 (US)

(72)	Inventors:
	BUCKINGHAM, Hailey Waterloo, ON N2K 0A7 (CA) BEVERIDGE, David, N. Waterloo, ON N2K 0A7 (CA)

(74)	Representative: Murgitroyd & Company
	165-169 Scotland Street Glasgow G5 8PL Glasgow G5 8PL (GB)

(56)

References cited: :

US-A1- 2017 220 929
US-A1- 2018 330 379

US-A1- 2018 013 772

FAKHR MOHAMED WALEED: "A multi-key compressed sensing and machine learning privacy preserving computing scheme", 2017 5TH INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL AND BUSINESS INTELLIGENCE (ISCBI), IEEE, 11 August 2017 (2017-08-11), pages 75 - 80, XP033159090, ISBN: 978-1-5386-1771-7, [retrieved on 20170928], DOI: 10.1109/ISCBI.2017.8053548
MKHAIL KAZDAGLI ET AL: "Exploiting Latent Attack Semantics for Intelligent Malware Detection", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 6 August 2017 (2017-08-06), XP080951659
TIANWEI ZHANG ET AL: "Privacy-preserving Machine Learning through Data Obfuscation", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 5 July 2018 (2018-07-05), XP081244226

Note: Within nine months from the publication of the mention of the grant of the European patent, any person may give notice to the European Patent Office of opposition to the European patent granted. Notice of opposition shall be filed in a written reasoned statement. It shall not be deemed to have been filed until the opposition fee has been paid. (Art. 99(1) European Patent Convention).