Explanation:
The best approach is to use an OAuth 2.0 access token issued by an external identity provider and verify it in a custom validation layer before accessing the model endpoint.
This method is widely used for secure, scalable, and flexible access control in enterprise environments.
Ultimate access to all questions.
Question: 33
You have deployed a machine learning model on Databricks for serving through a REST API. To ensure that only authorized users can access the model serving endpoint, you decide to implement token-based authentication. Which of the following is the best approach to control access to the model serving endpoint using token-based authentication?
A
Configure a Databricks Personal Access Token (PAT) for each user and validate it within the serving endpoint
B
Use an OAuth 2.0 access token issued by an external identity provider and verify it in a custom validation layer before accessing the model endpoint.
C
Use Databricks' built-in role-based access control (RBAC) and assign specific users access to the model serving endpoint via the workspace UI.
D
Set up API keys in Databricks Workspace and authenticate API requests by checking for the presence of a valid API key in each request.
