System and method for securing audio and video data for artificial intelligence operations on an information handling system

A method of securing audio-video user query input data on an information handling system executing an AI productivity tool software module for chatbot operations comprising:

• executing, with a hardware processor, computer-readable program code of a first unprivileged AI productivity-tool software process of operations of an AI productivity tool software module to request audio/video user query input data be recorded from a microphone or a video camera;
• receiving the audio/video user query input data at an audio/video (A/V) input stack buffer memory;
• executing computer-readable program code of an encryption key generator with the hardware processor that is associated with the first unprivileged AI productivity-tool software process to generate a first encryption key and transmit the first encryption key to an A/V encryption driver and securely transmit the first encryption key to a second unprivileged AI productivity-tool software process for operations of the AI productivity tool software module to identify a capability intent action responsive to the received audio/video user query input data;
• executing computer-readable program code of the A/V encryption filter driver to retrieve the audio/video user query input data from the A/V input stack buffer memory and use the first encryption key encrypt the audio/video user query input data for storage in an allocated encrypted storage buffer portion of the kernel system memory;
• and
• executing the computer-readable program code of the A/V encryption filter driver to send a handle describing the allocated kernel system memory to the second unprivileged AI productivity-tool software process for the second unprivileged AI productivity-tool software process to access the audio/video user query input data from the allocated encrypted storage buffer portion of the kernel system memory with the first encryption key.

An information handling system comprising:

• a hardware processor, a memory device including kernel system memory, and a power management unit to provide power to the hardware processor and memory device;
• the hardware processor to execute computer-readable program code instructions of a first unprivileged artificial intelligence (AI) productivity-tool software process for operations of an AI productivity tool software module to detect receipt of audio/video user query input data at an audio/video (A/V) input stack buffer memory that was recorded from a microphone or a video camera;
• the hardware processor to execute computer-readable program code of an encryption key generator associated with the first unprivileged AI productivity-tool software process to generate a first encryption key and transmit the first encryption key to an audio/video (A/V) encryption driver and to a second unprivileged AI productivity-tool software process for operations of the AI productivity tool software module;
• the hardware processor to execute computer-readable program code of the A/V encryption filter driver to retrieve the audio/video user query input data from the A/V input stack buffer memory and use the first encryption key encrypt the audio/video user query input data for storage in an allocated encrypted storage buffer portion of the kernel system memory;
• and
• the hardware processor to execute computer readable code instructions of the second unprivileged AI productivity-tool software process to retrieve and decrypt the audio/video user query input data using the first encryption key, process the audio/video user query input data in a second operation step of the AI productivity tool software module operations as second software process output, and encrypt the second software process output with a second encryption key received from a third unprivileged AI productivity-tool software process of the operations of the AI productivity tool software module operations to identify a capability intent action on the information handling system responsive to the received audio/video user query input data.