Systems and methods for detecting fake voice commands to smart devices
The present disclosure relates to detecting the use of fake voice command to activate microphones of smart devices. In one embodiment, sound characteristics associated with an audio signal from a microphone of smart device may be compared with other microphones of the smart device in order to detect fake voice commands. In another embodiment, sound characteristics associated with the audio signal from the microphone may be compared with a threshold range of stored sound characteristics in order to detect fake voice commands. In some embodiments, a controller may triangulate a position associated with a source of a sound in order to detect a fake voice command. In a further embodiment, a controller may verify that a user or associated electronic device are near a smart device to authorize a voice command.
1. A voice command verification system comprising:
one or more processors configured to execute computer-executable instructions stored on a non-transitory computer-readable medium, wherein the computer-executable instructions, when executed, cause the one or more processors to:
receive a light signal comprising an embedded audio command from a first microphone;
receive an audio signal from a second microphone in response to receiving the light signal from the first microphone;
determine a first characteristic of the light signal;
determine a second characteristic of the audio signal;
determine that the embedded audio command received via the first microphone is not authentic based on determining that the first characteristic does not correlate to the second characteristic; and
provide a notification in response to determining that the embedded audio command is not authentic.
2. The voice command verification system of claim 1 , wherein the first characteristic and the second characteristic each comprise one or more frequencies, wavelengths, amplitudes, wave speeds, waveforms, or any combination thereof.
3. The voice command verification system of claim 1 , wherein the one or more processors are configured to activate the second microphone in response to detection of the embedded audio command via the first microphone.
4. The voice command verification system of claim 1 , comprising one or more additional microphones wherein the first microphone, the second microphone and the one or more additional microphones each comprise micro-electromechanical system (MEMS) microphones.
5. The voice command verification system of claim 1 , wherein the one or more processors are configured to provide the notification via transmission to a separate smart device.
6. The voice command verification system of claim 1 , wherein the computer-executable instructions, when executed, cause the one or more processors to determine that the embedded audio command received via the first microphone and corresponding to the light signal is authentic based on determining that the first characteristic correlates to the second characteristic.
7. The voice command verification system of claim 1 , wherein the computer-executable instructions, when executed, cause the one or more processors to receive a third signal from a third microphone, determine a third characteristic of the third signal, and triangulate a location for a source of the embedded audio command based on the first characteristic, the second characteristic and the third characteristic.
8. The voice command verification system of claim 7 , wherein the computer-executable instructions, when executed, cause the one or more processors to determine that the embedded audio command received via the first microphone and corresponding to the light signal is not authentic based on determining that the first characteristic is not within a threshold range of the second characteristic based on the location being triangulated outside of a valid location range.
9. The voice command verification system of claim 1 , wherein the computer-executable instructions, when executed, cause the one or more processors to:
attempt to discover one or more electronic devices within a threshold distance of the voice command verification system;
determine that the embedded audio command is not authentic based on not detecting the one or more electronic devices within the threshold distance; and
determine that the embedded audio command is authentic based on detecting the one or more electronic devices within the threshold distance.
10. The voice command verification system of claim 1 , wherein the one or more processors are configured to:
send a verification form to one or more electronic devices based on determining that the embedded audio command was received; and
perform one or more actions related to the embedded audio command in response to validating the verification form received from the one or more electronic devices.
11. The voice command verification system of claim 1 , wherein the one or more processors are configured to determine that the embedded audio command is not authentic in response to receiving a reflected WiFi signal without an indication of a presence of a user within a threshold distance from the voice command verification system.
12. The voice command verification system of claim 1 , wherein the one or more processors are configured to determine that the embedded audio command is not authentic based on the first characteristic not being within a threshold range of one or more stored characteristics.