Systems and methods for detecting fake voice commands to smart devices

A smart device, comprising:

• at least one microphone;
• and
• one or more processors configured to:
• receive an embedded audio command embedded in a light signal from the at least one microphone;
• determine a speech rate associated with the embedded audio command;
• determine authenticity of the embedded audio command embedded in the light signal based on comparing the speech rate to a threshold speech rate, wherein the threshold speech rate is associated with an average human speech rate;
• and
• send a notification to one or more electronic devices based on the speech rate being above the threshold speech rate, wherein the notification indicates that the embedded audio command is fake.

One or more non-transitory, computer-readable media having computer-readable instructions that, when executed by one or more processors, cause the one or more processors to:

• receive a light signal from a first microphone of a plurality of microphones of a smart device, the light signal comprising an embedded audio command;
• receive data from one or more heat sensors communicatively coupled to the smart device;
• determine an authenticity of the embedded audio command based on the data from the one or more heat sensors, wherein the data indicates a position of a user;
• and
• send a notification to one or more electronic devices based on the data from the one or more heat sensors indicating that the user is not positioned within a threshold distance of the smart device, wherein the notification indicates that the embedded audio command is not authentic.