Model Armor and Sensitive Data Protection for the Agentic Architect Exam

GCP Study Hub
November 21, 2026

Hiding sensitive values inside an agent's reply without discarding the rest of the answer depends on which level of Sensitive Data Protection is configured in Model Armor. Model Armor offers two levels, basic and advanced, and the boundary between them determines whether sensitive values are only flagged or actually masked before a response reaches a user. For the Professional Agentic Architect exam, this distinction matters because several other Model Armor controls can detect violations or block output, yet only advanced Sensitive Data Protection masks individual matches while letting the rest of a response go through.

Basic vs. advanced Sensitive Data Protection

Basic Sensitive Data Protection supports inspection only, and it works solely with predefined infoTypes. It can flag values such as credit card numbers or US Social Security numbers in an agent's output, but it does not mask them. Even when basic inspection flags a match, the full value still reaches the user. Basic Sensitive Data Protection also cannot recognize custom formats, so an internal ID format falls outside what it can detect.

Advanced Sensitive Data Protection references Sensitive Data Protection templates instead of stopping at predefined inspection. This configuration pairs two templates that serve distinct roles:

  • An inspect template defines what to detect, covering predefined infoTypes as well as custom infoTypes such as a regular expression for an internal ID format.
  • A de-identify template masks each detected match while allowing the remainder of the response to pass through to the user.

When configuring advanced Sensitive Data Protection, every infoType listed in the de-identify template must also appear in the inspect template. Pairing both templates lets an agent keep delivering the useful portion of its answer while hiding the sensitive values inside it, whether those values are predefined formats like credit card numbers and US Social Security numbers or custom internal identifiers.

Pattern-based masking vs. model-dependent controls

Advanced Sensitive Data Protection is a deterministic control. Detection and masking follow fixed patterns rather than model behavior. A custom regex infoType matches text against a regular expression, so a value in a given format is detected by pattern rather than by judgment, the same way each time. The de-identify template then masks each match instead of only reporting it, and the rest of the text passes through.

Controls that work through a model behave differently. Prompt instructions, sampling settings such as temperature, and few-shot examples influence what a model writes, and safety classifier models such as Llama Guard judge content with a model of their own. Their results depend on model behavior, so they can make a sensitive value less likely to appear without guaranteeing that it never does. Blocking a whole response after a classifier flags it is also different from masking one value inside it.

How other Model Armor settings relate to masking

Sensitive Data Protection is one part of a Model Armor template, and the settings around it each have a distinct job. Knowing what each one does makes it clear that de-identification is the setting that masks part of a response.

  • The enforcement type decides what happens to a violation. Inspect and block stops the entire response, and inspect only detects the violation without blocking anything.
  • Floor settings define the minimum configuration that templates must meet. They govern how templates are configured rather than acting on content.
  • Confidence levels tune the responsible AI and prompt injection filters. They are not a Sensitive Data Protection setting.
  • Responsible AI filters look for harmful categories such as harassment or dangerous content.
  • The prompt injection and jailbreak filter looks for attacks in prompts.
  • The malicious URL filter checks links in the content.

Masking therefore comes from the advanced Sensitive Data Protection configuration, with an inspect template that defines what to find and a de-identify template that masks each match, where every infoType in the de-identify template also appears in the inspect template.

Our Professional Agentic Architect practice exams test Model Armor Sensitive Data Protection alongside responsible AI filters and prompt injection controls, with detailed explanations that drill these distinctions.

Get tips and updates from GCP Study Hub

arrow