Solution Overview
Deployment Scheme
Figure 1 Deployment diagram
For model protection in edge inference scenarios, there are logically the user management node, running node, and AI-GUARD (user host) node. They have the following functions:
- User management node: Provides centralized key control services, controls master keys and pre-shared keys, and deploys encryption and decryption working keys.
- Running node: Executes inference jobs.
- AI-GUARD node: Provides the CLI encryption tool to encrypt data for local use.
Parent topic: Networking Solution