US 11,114,104 B2 · Preventing adversarial audio attacks on digital assistants

Abstract

Aspects of the present invention disclose a method for preventing adversarial audio attacks through detecting and isolating inconsistencies utilizing beamforming techniques and IoT devices. The method includes one or more processors identifying an audio command received by a listening device. The method further includes determining a source location of the audio command utilizing a sensor array of the listening device. The method further includes determining a location of a user in relation to the listening device based on data of an Internet of Things (IoT) device. The method further includes determining an inconsistency between the determines source location and the determined location of the user based at least in part on data of the sensor array and data of the IoT device.

Claims20

Dependent claims

A method comprising:

identifying, by one or more processors, an audio command received by a listening device;
determining, by one or more processors, a source location of the audio command utilizing a sensor array of the listening device;
determining, by one or more processors, a location of a user in relation to the listening device based on data of an Internet of Things (IoT) device;
determining, by one or more processors, an inconsistency between the determined source location and the determined location of the user based at least in part on data of the sensor array and data of the IoT device;
and
determining, by one or more processors, a rank of the inconsistency based at least in part on factors of the inconsistency, wherein the factors include a score value and confidence level value.

3 more elements

A computer program product comprising:

one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising:
program instructions to identify an audio command received by a listening device;
program instructions to determine a source location of the audio command utilizing a sensor array of the listening device;
program instructions to determine a location of a user in relation to the listening device based on data of an Internet of Things (IoT) device;
program instructions to determine an inconsistency between the determined source location and the determined location of the user based at least in part on data of the sensor array and data of the IoT device;
and
program instructions to determine a rank of the inconsistency based at least in part on factors of the inconsistency, wherein the factors include a score value and confidence level value.

4 more elements

A computer system comprising:

one or more computer processors;
one or more computer readable storage media;
and
program instructions stored on the computer readable storage media for execution by at least one of the one or more processors, the program instructions comprising:
program instructions to identify an audio command received by a listening device;
program instructions to determine a source location of the audio command utilizing a sensor array of the listening device;
program instructions to determine a location of a user in relation to the listening device based on data of an Internet of Things (IoT) device;
program instructions to determine an inconsistency between the determined source location and the determined location of the user based at least in part on data of the sensor array and data of the IoT device;
and
program instructions to determine a rank of the inconsistency based at least in part on factors of the inconsistency, wherein the factors include a score value and confidence level value.

7 more elements

Dependencies are inferred from the claim text.

Preventing adversarial audio attacks on digital assistants

Life of this patent

Preventing adversarial audio attacks on digital assistants

Life of this patent

Abstract

Claims20