Certified Generative AI Engineer AssociateDemo

By Databricks · Question Mode

QuestionQ18

Governance

A Generative AI Engineer is deploying a customer-facing, fine-tuned LLM to the company’s public website. Because the company made a large investment in fine-tuning this model and the tuning data is proprietary, they are concerned about model inversion attacks.

Which Databricks AI Security Framework (DASF) risk-mitigation strategies below are most relevant to this scenario?

Choose two
  • A Implement AI guardrails to allow users to configure and enforce compliance
  • B Leverage Databricks access control lists (ACLs) to configure permissions for accessing models
  • C Use secure model features with Databricks Feature Store
  • D Apply attribute-based access controls (ABAC) to limit unauthorized access
Explanation

Model inversion can expose private training information by exploiting access to a model and its outputs. Restricting model access with ACLs and enforcing fine-grained attribute-based authorization reduce the ability of unauthorized parties to access or repeatedly invoke the proprietary model. Databricks ACLs control permissions on workspace objects, including MLflow models, and Unity Catalog ABAC centralizes scalable access policies based on governed tags.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!