Microsoft DP-100 Exam - Topic 9 Question 44 Discussion

Actual exam question for Microsoft's DP-100 exam

Question #: 44
Topic #: 9

[All DP-100 Questions]

You have a dataset that includes confidential dat

a. You use the dataset to train a model.

You must use a differential privacy parameter to keep the data of individuals safe and private.

You need to reduce the effect of user data on aggregated results.

What should you do?

ADecrease the value of the epsilon parameter to reduce the amount of noise added to the data

BIncrease the value of the epsilon parameter to decrease privacy and increase accuracy

CDecrease the value of the epsilon parameter to increase privacy and reduce accuracy

DSet the value of the epsilon parameter to 1 to ensure maximum privacy

Show Suggested Answer

Suggested Answer: C

Differential privacy tries to protect against the possibility that a user can produce an indefinite number of reports to eventually reveal sensitive data. A value known as epsilon measures how noisy, or private, a report is. Epsilon has an inverse relationship to noise or privacy. The lower the epsilon, the more noisy (and private) the data is.

https://docs.microsoft.com/en-us/azure/machine-learning/concept-differential-privacy

by Melodie at May 09, 2022, 06:11 PM

Limited Time Offer

25%

Off

Get Premium DP-100 Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

Submit Cancel

Felix

4 months ago

Just to clarify, decreasing epsilon adds noise, right?

upvoted 0 times

...

Henriette

4 months ago

B is a no-go! We need to prioritize privacy over accuracy.

upvoted 0 times

...

Micah

5 months ago

Wait, isn't D a bit misleading? Epsilon of 1 isn't maximum privacy.

upvoted 0 times

...

Timmy

5 months ago

Totally agree with C! Privacy is key here.

upvoted 0 times

...

Rolande

5 months ago

C is the right choice! Lower epsilon means better privacy.

upvoted 0 times

...

Nettie

5 months ago

I vaguely remember that setting epsilon to 1 is not the best choice for privacy. I think lower values are better for protecting individual data.

upvoted 0 times

...

Tarra

5 months ago

I feel like option C makes sense because it mentions increasing privacy, but I can't recall if reducing accuracy is a big issue.

upvoted 0 times

...

Lenita

5 months ago

I practiced a similar question where increasing epsilon meant less privacy but better accuracy. I wonder if that's the same here.

upvoted 0 times

...

Mose

5 months ago

I think I remember that decreasing epsilon increases privacy, but I'm not sure if it also reduces accuracy.

upvoted 0 times

...

Franchesca

5 months ago

Hmm, this looks like a tricky networking question. I'll need to carefully read through the options and think about the implications of each choice.

upvoted 0 times

...

Staci

5 months ago

Okay, let's see. Since the instances are configured to block project-wide SSH keys, that rules out option D. I'm leaning towards option C, but I'll double-check the details.

upvoted 0 times

...

Skye

5 months ago

Application Insights Profiler is great for in-depth performance analysis, but it doesn't sound like the right fit for this question. I'm leaning towards Smart Detection or Continuous export.

upvoted 0 times

...

Dalene

5 months ago

I think I've got this one figured out. The key is to use a load balancer that can handle path-based routing, which would be the most efficient way to route traffic to the different microservices. Option C, the Application Load Balancer, seems like the best choice here.

upvoted 0 times

...