US 12,445,414 B2
Security-based artificial intelligence workload allocation in a heterogeneous environment
John Kelly, Cork (IE); Balasubramanian Chandrasekaran, Austin, TX (US); and Dharmesh M. Patel, Round Rock, TX (US)
Assigned to Dell Products L.P., Round Rock, TX (US)
Filed by Dell Products L.P., Round Rock, TX (US)
Filed on Jan. 23, 2024, as Appl. No. 18/419,771.
Prior Publication US 2025/0240276 A1, Jul. 24, 2025
Int. Cl. H04L 29/06 (2006.01); G06F 18/2415 (2023.01); H04L 9/40 (2022.01)
CPC H04L 63/0272 (2013.01) [G06F 18/2415 (2023.01)] 17 Claims
OG exemplary drawing
 
1. A method for managing workload placement, the method comprising:
obtaining, by a variant selection agent of a workload placement service and from a front-end device, a request for an inferencing payload generated by an inferencing workload and wherein the request includes sensitive information;
in response to the request:
performing a payload classification on the request to determine a variant selection for the inferencing workload, wherein the variant selection is one selected from the group consisting of a secured variant and a public variant and based on the inclusion of the sensitive information in the request;
selecting, based on the payload classification, the secure variant as the variant selection;
in response to the selection, transmitting the request to the secured variant, wherein the secured variant executes an instance of the inferencing workload on a secured production environment;
obtaining, from the secured variant, the requested inferencing payload, wherein the requested inferencing payload is generated by the secured variant executing a generative artificial intelligence (AI) model; and
providing, after the obtaining, the requested inferencing payload to the front-end device.