(12) International Application Status Report

Received at International Bureau: 04 December 2019 (04.12.2019)

Information valid as of: 20 May 2020 (20.05.2020)

Report generated on: 27 September 2020 (27.09.2020)

(10) Publication number: (43) Publication date: (26) Publication language:
WO 2020/10977404 June 2020 (04.06.2020) English (EN)

(21) Application number: (22) Filing date: (25) Filing language:
PCT/GB2019/05333526 November 2019 (26.11.2019) English (EN)

(31) Priority number(s): (32) Priority date(s): (33) Priority status:
1819211.2 (GB)26 November 2018 (26.11.2018) Priority document received (in compliance with PCT Rule 17.1)

(51) International Patent Classification:
G06N 3/04 (2006.01); G06N 5/00 (2006.01); G06N 3/08 (2006.01)

(71) Applicant(s):
IMPERIAL COLLEGE OF SCIENCE, TECHNOLOGY AND MEDICINE [GB/GB]; South Kensington Campus Faculty Building Exhibition Road London SW7 2AZ (GB) (for all designated states)

(72) Inventor(s):
LOMUSCIO, Alessio; c/o Imperial College of Science, Technology and Medicine South Kensington Campus Faculty Building, Exhibition Road London SW7 2AZ (GB)
PANAGIOTIS, Kouvaros; c/o Imperial College of Science, Technology and Medicine South Kensington Campus, Faculty Building, Exhibition Road London SW7 2AZ (GB)

(74) Agent(s):
THORNILEY, Peter; Venner Shipley LLP 200 Aldersgate London EC1A 4HD (GB)

(54) Title (EN): VERIFICATION OF PERCEPTION SYSTEMS
(54) Title (FR): VÉRIFICATION DE SYSTÈMES DE PERCEPTION

(57) Abstract:
(EN): There is provided a computer-implemented method for verifying the robustness of a neural network classifier with respect to one or more parameterised transformations applied to an input, the classifier comprising one or more convolutional layers, the method comprising: encoding each layer of the classifier as one or more algebraic classifier constraints; encoding each transformation as one or more algebraic transformation constraints; encoding a change in an output classifier label from the classifier as an algebraic output constraint; determining whether a solution exists which satisfies the classifier constraints, transformation constraints and output constraints, and determining the classifier as robust to the local transformations if no such solution exists. A perception system and a computer readable medium are also provided.
(FR): L'invention concerne un procédé mis en Ĺ“uvre par ordinateur pour vérifier la robustesse d'un classificateur de réseau neuronal par rapport à une ou plusieurs transformations paramétrées appliquées à une entrée, le classificateur comprenant une ou plusieurs couches de convolution, le procédé consistant : à coder chaque couche du classificateur sous la forme d'une ou de plusieurs contraintes de classificateur algébriques ; à coder chaque transformation sous la forme d'une ou de plusieurs contraintes de transformation algébriques ; à coder un changement dans une étiquette de classificateur de sortie à partir du classificateur sous la forme d'une contrainte de sortie algébrique ; à déterminer si une solution existe qui satisfait les contraintes de classificateur, les contraintes de transformation et les contraintes de sortie, et à déterminer le classificateur comme robuste aux transformations locales si aucune pareille solution n'existe. L'invention porte également sur un système de perception et sur un support lisible par ordinateur.

International search report:
Received at International Bureau: 01 April 2020 (01.04.2020) [EP]

International Report on Patentability (IPRP) Chapter II of the PCT:
Not available

(81) Designated States:
AE, AG, AL, AM, AO, AT, AU, AZ, BA, BB, BG, BH, BN, BR, BW, BY, BZ, CA, CH, CL, CN, CO, CR, CU, CZ, DE, DJ, DK, DM, DO, DZ, EC, EE, EG, ES, FI, GB, GD, GE, GH, GM, GT, HN, HR, HU, ID, IL, IN, IR, IS, JO, JP, KE, KG, KH, KN, KP, KR, KW, KZ, LA, LC, LK, LR, LS, LU, LY, MA, MD, ME, MG, MK, MN, MW, MX, MY, MZ, NA, NG, NI, NO, NZ, OM, PA, PE, PG, PH, PL, PT, QA, RO, RS, RU, RW, SA, SC, SD, SE, SG, SK, SL, SM, ST, SV, SY, TH, TJ, TM, TN, TR, TT, TZ, UA, UG, US, UZ, VC, VN, ZA, ZM, ZW
European Patent Office (EPO) : AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LT, LU, LV, MC, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR
African Intellectual Property Organization (OAPI) : BF, BJ, CF, CG, CI, CM, GA, GN, GQ, GW, KM, ML, MR, NE, SN, TD, TG
African Regional Intellectual Property Organization (ARIPO) : BW, GH, GM, KE, LR, LS, MW, MZ, NA, RW, SD, SL, ST, SZ, TZ, UG, ZM, ZW
Eurasian Patent Organization (EAPO) : AM, AZ, BY, KG, KZ, RU, TJ, TM