During the selection of a machine learning (ML)-based threat classification model, a cybersecurity administrator verifies that label distribution is highly unbalanced. Which of the following…

The correct answer is B. Data augmentation. When label distribution is highly unbalanced, data augmentation generates additional synthetic samples for the underrepresented classes. This balances the dataset, improving the ML model's ability to classify threats accurately across all categories.

Security Architecture and Tool Sets

Question

During the selection of a machine learning (ML)-based threat classification model, a cybersecurity administrator verifies that label distribution is highly unbalanced. Which of the following processing techniques should the engineer use to balance the model?

Options

AData lineage
BData augmentation
CData provenance
DData verification

How the community answered

(27 responses)

A
4% (1)
B
85% (23)
C
7% (2)
D
4% (1)

Explanation

When label distribution is highly unbalanced, data augmentation generates additional synthetic samples for the underrepresented classes. This balances the dataset, improving the ML model's ability to classify threats accurately across all categories.

Topics

#ML model training#data augmentation#class imbalance#threat classification

Community Discussion

No community discussion yet for this question.

Full CY0-001 Practice