Deal of The Day! Hurry Up, Grab the Special Discount - Save 25% - Ends In 00:00:00 Coupon code: SAVE25
Welcome to Pass4Success

- Free Preparation Discussions
Mail Us support@pass4success.com
Location US
Mob_nav_barsMENU

Google Professional Machine Learning Engineer Exam - Topic 10 Question 59 Discussion

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

Google Professional Machine Learning Engineer Exam - Topic 10 Question 59 Discussion

Actual exam question for Google's Professional Machine Learning Engineer exam
Question #: 59
Topic #: 10
[All Professional Machine Learning Engineer Questions]

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

Show Suggested Answer Hide Answer
Suggested Answer: D

This approach would allow you to keep the critical columns of data while reducing the sensitivity of the dataset by removing the personally identifiable information (PII) before training the model. By creating an authorized view of the data, you can ensure that sensitive values cannot be accessed by unauthorized individuals.


by Leatha at Feb 04, 2023, 06:10 AM

Limited Time Offer

25%

Off

Get Premium Professional Machine Learning Engineer Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

0/2000 characters
Submit Cancel
Heike
10 months ago
Definitely go with C, replacing sensitive data is a must!
upvoted 0 times
...
Jose
10 months ago
I think D is too limiting, we need all columns for training!
upvoted 0 times
...
Brynn
10 months ago
Wait, can we really just encrypt with AES-256? Seems risky!
upvoted 0 times
...
Audra
11 months ago
I disagree, randomizing values (A) might mess with data integrity.
upvoted 0 times
...
Jenise
11 months ago
Option B sounds solid, DLP is key for sensitive data!
upvoted 0 times
...
Ivette
11 months ago
I recall that simply removing sensitive columns might not be ideal since every column is critical. We need to ensure we still have usable data after processing.
upvoted 0 times
...
Cory
11 months ago
I'm leaning towards option B, but I’m a bit confused about the difference between Format Preserving Encryption and just regular encryption.
upvoted 0 times
...
Bea
11 months ago
I think using the DLP API is a good approach since it can help identify sensitive data. I practiced a similar question where we had to mask data before analysis.
upvoted 0 times
...
Lynelle
11 months ago
I remember we discussed the importance of protecting PII in our data science class, but I'm not sure which method is best for this scenario.
upvoted 0 times
...
Ozell
11 months ago
I've got this! Versa CPEs support admission control, hierarchical queuing, and egress policing. Easy peasy.
upvoted 0 times
...
Jenifer
11 months ago
Hmm, I'm not too familiar with the Material Workbench, so I'll need to read the options carefully.
upvoted 0 times
...

Save Cancel