Google Cloud Professional Machine Learning Engineer — Question 140

You are training an ML model using data stored in BigQuery that contains several values that are considered Personally Identifiable Information (PII). You need to reduce the sensitivity of the dataset before training your model. Every column is critical to your model. How should you proceed?

Answer options

• A. Using Dataflow, ingest the columns with sensitive data from BigQuery, and then randomize the values in each sensitive column.
• B. Use the Cloud Data Loss Prevention (DLP) API to scan for sensitive data, and use Dataflow with the DLP API to encrypt sensitive values with Format Preserving Encryption.
• C. Use the Cloud Data Loss Prevention (DLP) API to scan for sensitive data, and use Dataflow to replace all sensitive data by using the encryption algorithm AES-256 with a salt.
• D. Before training, use BigQuery to select only the columns that do not contain sensitive data. Create an authorized view of the data so that sensitive values cannot be accessed by unauthorized individuals.

Correct answer: B

Explanation

The correct answer is B because it effectively identifies sensitive data and uses Format Preserving Encryption to encrypt those values while maintaining the structure necessary for the model. Option A does not ensure data protection as randomization may still expose PII patterns, option C replaces sensitive data but does not preserve its format, and option D eliminates sensitive data columns entirely, which is not suitable when all columns are critical for the model.