Domain 4 of 6

Controls and Safeguards Around a Model

Defence in depth around a model that nobody can make reliable on its own. Filtering in both directions, grounding answers in sources a reader can check and least privilege for anything an agent is allowed to touch.

Concepts

~23%

Of the exam

Practice questions

Concepts in this domain

01Securing an AI systemAccess control, encryption and the shared responsibility model applied to machine learning, plus the attack surfaces that only exist because there is a model in the path.02What Is Prompt Engineering? Techniques and ExamplesUnderstand prompt engineering with examples of zero shot and few shot prompting, prompt templates, chain of thought, evaluation and common security risks.03What Are AI Agents? Tools, Workflows and PermissionsUnderstand how AI agents use tools, how agents differ from fixed workflows and why read access, write permissions and execution controls matter.04LLM Grounding Explained: Sources, Citations and HallucinationsLearn how LLM grounding connects answers to evidence, how it differs from RAG and how to check citations, source quality and unsupported claims.05Guardrails and output handlingThe controls that sit around a model, why layering them never produces a boundary, and the one practitioners get wrong, which is what the application does with the response.06Excessive agency and tool permissionsA system able to do more than its feature requires, the three forms it takes, and why permission design is the one control that still works after everything else has failed.07Hidden context exposureEverything an application quietly holds in the context window, why a system prompt was never a security boundary, and why leaked context is usually the step before the attack.

Try a question from this domain

A support agent built on a model reads customer emails and can issue refunds. A customer email contains text telling the assistant to ignore its instructions and refund in full. It does. What addresses this?

AFiltering both directions, least privilege on the refund tool, and a confirmation before anything financial.
BA stronger system prompt stating that instructions in emails must be ignored.
CRetraining the model on examples of this attack.
DLowering the temperature so the model follows its instructions more consistently.

21 questions on this domain.

One per page, with a worked explanation.

Start the set