Systems and methods for real time deepfake identification in virtual meetings

1 . A method, comprising:

initiating, in a first device, an instance of a virtual meeting in response to receiving access credential of a user;

responsive to initiating the instance, generating, in a second device remotely located from the first device over a cloud network, a cryptographic key unique to the user and the instance;

sending instructions from the second device to a device application executing in a third device associated with the user, the third device being remotely located from the second device over the cloud network, wherein the device application causes the third device to generate and emit an ultrasonic signal encoding the cryptographic key according to the instructions;

receiving, at the second device, in real time from the virtual meeting executing in the first device, audio data associated with the access credential;

searching, at the second device, the audio data for the ultrasonic signal;

responsive to finding the ultrasonic signal in the audio data, categorizing at the second device, the access credential as authentic and allowing the access credential into the virtual meeting executing in the first device; and

responsive to not finding the ultrasonic signal in the audio data, categorizing at the second device the access credential as unauthentic and rejecting the access credential from the virtual meeting executing in the first device.

2 . The method of claim 1 , further comprising repeating sending the instructions to generate and emit the ultrasonic signal, receiving the audio data, searching the audio data for the ultrasonic signal, and allowing or rejecting the access credential according to a predetermined schedule.

3 . The method of claim 2 , wherein the ultrasonic signal is different in each repetition.

4 . The method of claim 1 , wherein the first device is different from the third device.

5 . The method of claim 1 , wherein the first device is same as the third device.

6 . The method of claim 1 , wherein the third device is a smartphone.

7 . The method of claim 1 , further comprising analyzing the audio data to determine proximity of the first device to the user.

8 . Non-transitory computer-readable tangible media that includes instructions for execution, which when executed by a processor of a first computing device, is operable to perform operations comprising:

initiating, in a second computing device remotely located from the first computing device over a cloud network, an instance of a virtual meeting in response to receiving access credential of a user;

responsive to initiating the instance, generating, in the first computing device, a cryptographic key unique to the user and the instance;

sending instructions from the first computing device to a device application executing in a third computing device associated with the user, the third computing device being remotely located from the first computing device over the cloud network, wherein the device application causes the third computing device to generate and emit an ultrasonic signal encoding the cryptographic key according to the instructions;

receiving, at the first computing device, in real time from the virtual meeting executing in the second computing device, audio data associated with the access credential;

searching, at the first computing device, the audio data for the ultrasonic signal;

responsive to finding the ultrasonic signal in the audio data, categorizing, at the first computing device, the access credential as authentic and allowing the access credential into the virtual meeting; and

responsive to not finding the ultrasonic signal in the audio data, categorizing, at the first computing device, the access credential as unauthentic and rejecting the access credential from the virtual meeting.

9 . The non-transitory computer-readable tangible media of claim 8 , wherein the operations further comprise repeating sending the instructions to generate and emit the ultrasonic signal, receiving the audio data, searching the audio data for the ultrasonic signal, and allowing or rejecting the access credential according to a predetermined schedule.

10 . The non-transitory computer-readable tangible media of claim 9 , wherein the ultrasonic signal is different in each repetition.

11 . The non-transitory computer-readable tangible media of claim 8 , wherein the second computing device is different from the third computing device.

12 . The non-transitory computer-readable tangible media of claim 8 , wherein the second computing device is same as the third device.

13 . The non-transitory computer-readable tangible media of claim 8 , wherein the third computing device is a smartphone.

14 . The non-transitory computer-readable tangible media of claim 8 , wherein the operations further comprise analyzing the audio data to determine proximity of the second computing device to the user.

15 . An apparatus comprising:

a processing circuitry;

a memory storing data; and

a communication circuitry, wherein the processing circuitry executes instructions associated with the data, the processing circuitry is coupled to the communication circuitry and the memory, and the processing circuitry and the memory cooperate, such that the apparatus is configured for:

initiating, at a first device remotely located from the apparatus over a cloud network, an instance of a virtual meeting in response to receiving access credential of a user;

responsive to initiating the instance, generating a cryptographic key unique to the user and the instance;

sending instructions to a device application executing in a second device associated with the user, the second device being remotely located from the apparatus over the cloud network, wherein the device application causes the second device to generate and emit an ultrasonic signal encoding the cryptographic key according to the instructions;

receiving in real time from the virtual meeting executing in the first device, audio data associated with the access credential;

searching the audio data for the ultrasonic signal;

responsive to finding the ultrasonic signal in the audio data, categorizing the access credential as authentic and allowing the access credential into the virtual meeting; and

responsive to not finding the ultrasonic signal in the audio data, categorizing the access credential as unauthentic and rejecting the access credential from the virtual meeting.

16 . The apparatus of claim 15 , further configured for repeating sending the instructions to generate and emit the ultrasonic signal, receiving the audio data, searching the audio data for the ultrasonic signal, and allowing or rejecting the access credential according to a predetermined schedule.

17 . The apparatus of claim 16 , wherein the ultrasonic signal is different in each repetition.

18 . The apparatus of claim 15 , wherein the second device is different from the first device.

19 . The apparatus of claim 15 , wherein the first device is same as the second device.

20 . The apparatus of claim 15 , further configured for analyzing the audio data to determine proximity of the first device to the user.