nerdexam
Google

PROFESSIONAL-CLOUD-SECURITY-ENGINEER · Question #327

Your organization is developing a sophisticated machine learning (ML) model to predict customer behavior for targeted marketing campaigns. The BigQuery dataset used for training includes sensitive…

The correct answer is A. De-identify sensitive data before model training by using Cloud Data Loss Prevention (DLP)APIs. Data De-identification: De-identifying sensitive data using Cloud DLP APIs ensures that the data used for model training does not contain personally identifiable information (PII). This protects data privacy and reduces the risk of unauthorized access or misuse. IAM Policies…

Submitted by salim_om· Apr 18, 2026Ensuring data protection

Question

Your organization is developing a sophisticated machine learning (ML) model to predict customer behavior for targeted marketing campaigns. The BigQuery dataset used for training includes sensitive personal information. You must design the security controls around the AI/ML pipeline. Data privacy must be maintained throughout the model's lifecycle and you must ensure that personal data is not used in the training process. Additionally, you must restrict access to the dataset to an authorized subset of people only. What should you do?

Options

  • ADe-identify sensitive data before model training by using Cloud Data Loss Prevention (DLP)APIs.
  • BImplement Identity-Aware Proxy to enforce context-aware access to BigQuery and models based
  • CImplement at-rest encryption by using customer-managed encryption keys (CMEK) for the
  • DDeploy the model on Confidential VMs for enhanced protection of data and code while in use.

How the community answered

(26 responses)
  • A
    81% (21)
  • B
    12% (3)
  • C
    4% (1)
  • D
    4% (1)

Explanation

Data De-identification: De-identifying sensitive data using Cloud DLP APIs ensures that the data used for model training does not contain personally identifiable information (PII). This protects data privacy and reduces the risk of unauthorized access or misuse. IAM Policies: Implementing strict IAM policies controls access to BigQuery, ensuring that only authorized personnel can access and use the dataset. This further protects data privacy and reduces the risk of unauthorized access. Comprehensive Approach: This approach combines data de-identification and IAM controls to provide a robust and effective security solution for the AI/ML pipeline.

Topics

#Data De-identification#Cloud Data Loss Prevention (DLP)#BigQuery Security#ML Data Privacy

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full PROFESSIONAL-CLOUD-SECURITY-ENGINEER Practice