British Telecommunications Public Limited Company

Gabriele Gelardi

Gery Ducatel

Ali Sajjad

There is provided a computer implemented method for accessing a resource at a computing device, as well as for controlling access to a resource by a computing device. The computing device receives a policy indicating a set of conditions under which access to the resource is permitted, determines whether each of the conditions are initially present based on an output of one or more sensors of the device, and monitors the one or more sensors to detect a change in the presence of one or more of the conditions. In response to detecting the change in the presence of one or more of the conditions, the computing device determines whether each of the conditions are present. In response to determining that each of the conditions is present, access to the resource is enabled. If at least one of the conditions is not present, access to the resource is prevented.

Resource access control

A computer implemented method of access control for a user device having at least one component for determining behaviors of the user. The method including defining a training period during which access to the device is determined based on a credential-based authentication scheme wherein each access determination is used to generate an item of training data and training a machine learning classifier based on the training data such that the classifier is operable to classify user behavior as compliant or non-compliant. The method further including, in response to a determination that a behavior subsequent to the training period is classified as non-compliant, requesting a credential-based authentication of the user and permitting access to the device in response to the credential-based authentication, wherein permitting access to the device further includes constructively training the classifier based on the subsequent behavior as a compliant behavior.

Access control classifier training

Computer implemented methods for enrolling a user as an authenticated user of a computing device and for authenticating a user of a computing device are provided. The methods make use of behavioral biometrics to determine a set of shares that represent a secret credential according to a secret sharing scheme. The set of shares is initially determined when the user is enrolled based on typical measurements of the user's behavioral biometrics and authentication data indicating how to generate the set of shares from a user's behavioral biometrics is generated. When authenticating the user, the computing device can generate the set of shares based on the authentication data and measurements of the current user's behavioral biometrics. The computing device can use the generated set of shares to recreate a copy of the secret credential with which to authenticate the user.

User authentication based on behavioral biometrics

A computer implemented method of access control for a user device having at least one component for determining behaviors of the user. The method including accessing a first machine learning classifier trained based on at least one prior behavior of the user using the device, the classifier classifying user behavior as compliant or non-compliant. The method further including, in response to a determination that a subsequent behavior is classified as non-compliant, accessing a second machine learning classifier trained based on at least one prior behavior of the user using the device where the prior behavior is classified as non-compliant by the first classifier. The method further including, in response to a determination that the subsequent behavior is classified as non-compliant by the second classifier, requesting a credential-based authentication of the user and constructively training one of the machine learning classifiers based on the credential-based authentication result.

Growing community of inventors

London, United Kingdom

Gabriele Gelardi