Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020112101 - SYSTEM AND METHOD FOR CONTROLLING ACCESS TO DATA

Publication Number WO/2020/112101
Publication Date 04.06.2020
International Application No. PCT/US2018/062796
International Filing Date 28.11.2018
IPC
G06F 21/62 2013.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
21Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
60Protecting data
62Protecting access to data via a platform, e.g. using keys or access control rules
CPC
G06F 21/6218
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
21Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
60Protecting data
62Protecting access to data via a platform, e.g. using keys or access control rules
6218to a system of files or objects, e.g. local or distributed file system or database
G06F 21/6245
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
21Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
60Protecting data
62Protecting access to data via a platform, e.g. using keys or access control rules
6218to a system of files or objects, e.g. local or distributed file system or database
6245Protecting personal data, e.g. for financial or medical purposes
G06F 2221/2141
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
2221Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
21Indexing scheme relating to G06F21/00 and subgroups addressing additional information or applications relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
2141Access rights, e.g. capability lists, access control lists, access tables, access matrices
G06F 2221/2149
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
2221Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
21Indexing scheme relating to G06F21/00 and subgroups addressing additional information or applications relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
2149Restricted operating environment
Applicants
  • OLYMPUS CORPORATION [JP]/[JP]
  • LANSEL, Steven Paul [US]/[US]
Inventors
  • LANSEL, Steven Paul
Agents
  • HOLTZ, Leonard
  • TIDWELL, Mark A.
  • BORLAND, Harold
  • RAJ, Vinu
Priority Data
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SYSTEM AND METHOD FOR CONTROLLING ACCESS TO DATA
(FR) SYSTÈME ET PROCÉDÉ PERMETTANT DE CONTRÔLER L'ACCÈS À DES DONNÉES
Abstract
(EN)
A method for evaluating external neural network models while limiting access to internal training data includes providing labeled training data from a first source, receiving, by the first source, a neural network model from a second source different from the first source, blocking, by the first source, access by the second source to the labeled training data, and training, by the first source, the neural network model according to a supervised machine learning process using the labeled training data. The method further includes generating a first set of metrics from the supervised machine learning process that provide feedback about training of the neural network model, analyzing the first set of metrics to identify any subset data therein, and, in order to permit evaluation of the neural network model, transmitting to the second source those metrics that do not include the subset data.
(FR)
L'invention concerne un procédé permettant d'évaluer des modèles de réseau neuronal externes tout en limitant l'accès à des données d'apprentissage internes, consistant à fournir des données d'apprentissage étiquetées d'une première source, à recevoir, par la première source, un modèle de réseau neuronal d'une seconde source différente de la première source, à bloquer, par la première source, un accès par la seconde source aux données d'apprentissage étiquetées, et à entraîner, par la première source, le modèle de réseau neuronal selon un processus d'apprentissage machine supervisé à l'aide des données d'apprentissage étiquetées. Le procédé consiste en outre à générer un premier ensemble de mesures, provenant du processus d'apprentissage machine supervisé, fournissant une rétroaction concernant l'apprentissage du modèle de réseau neuronal, à analyser le premier ensemble de mesures pour identifier n'importe quel sous-ensemble de données s'y trouvant et, afin de permettre l'évaluation du modèle de réseau neuronal, à transmettre à la seconde source lesdites mesures qui ne comprennent pas les données du sous-ensemble.
Latest bibliographic data on file with the International Bureau