BEHAVIOR MODELING USING CLIENT-HOSTED NEURAL NETWORKS

Apparatuses, systems, and techniques to detect abnormal behavior on clients using one or more neural networks on said clients. In at least one embodiment, use of or behavior on one or more clients is analyzed by a first neural network to detect abnormal behavior compared to a baseline of accepted be...

Full description

Saved in:
Bibliographic Details
Main Authors WOODARD, Andrew James, WAINE, Benjemin Thomas, ROSE, Amy Leigh, SCHNEIDER, Christopher Ian
Format Patent
LanguageEnglish
French
Published 16.12.2021
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC COMMUNICATION TECHNIQUE
ELECTRIC DIGITAL DATA PROCESSING
ELECTRICITY
PHYSICS
TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION
Online AccessGet full text

Cover

More Information
Summary:Apparatuses, systems, and techniques to detect abnormal behavior on clients using one or more neural networks on said clients. In at least one embodiment, use of or behavior on one or more clients is analyzed by a first neural network to detect abnormal behavior compared to a baseline of accepted behavior, and said baseline of accepted behavior is revised over time by a second neural network based on behavior observed on said one or more clients. Des appareils, des systèmes et des techniques pour détecter un comportement anormal chez des clients à l'aide d'un ou de plusieurs réseaux neuronaux desdits clients. Dans au moins un mode de réalisation, l'utilisation ou le comportement d'un ou de plusieurs clients est analysé par un premier réseau neuronal pour détecter un comportement anormal par rapport à une ligne de base du comportement accepté, et ladite ligne de base de comportement accepté est révisée au fil du temps par un second réseau neuronal sur la base d'un comportement observé du ou desdits clients.
Bibliography:Application Number: WO2021US36677