2.1 Recommend AI-powered Data Analytic Techniques to Meet Specific Needs or Answer Specific Questions 350-201 Practice Questions (Page 6)

Questions 26–30

1. 26foundation · easy

   What is the primary purpose of anomaly detection in cybersecurity?

   • ATo predict the exact number of future attacks
   • BTo assign labels to known malware families
   • CTo group similar network flows together
   • DTo identify data points that deviate significantly from normal behavior
   Reveal Solution Discussion Select an answer first
2. 27foundation · easy

   What is the primary purpose of ensemble methods in AI analytics?

   • ATo combine multiple models to improve accuracy and robustness
   • BTo label data for supervised learning
   • CTo reduce the number of features in the dataset
   • DTo visualize data in a graph
   Reveal Solution Discussion Select an answer first
4. 28application · medium

   A security team is building a model to detect phishing emails. They have a dataset with many features, and individual models (decision trees, logistic regression, etc.) show high variance and inconsistent performance across different test sets. They want to improve the overall accuracy and robustness of the detection. Which approach should they take?

   • AUse an ensemble method that combines multiple models
   • BUse a single deep neural network with more layers
   • CUse regression to predict a phishing score
   • DUse clustering to group emails before classification
   Reveal Solution Discussion Select an answer first
5. 29foundation · easy

   Which scenario would benefit most from graph analytics?

   • AIdentifying the shortest path an attacker could take from an external host to a critical server
   • BClassifying network traffic as malicious or benign
   • CPredicting the number of malware infections next month
   • DDetecting anomalies in CPU usage
   Reveal Solution Discussion Select an answer first
6. 30application · medium

   A security team has developed a machine learning model to detect malware. In their test set, the model correctly identified 95% of all malware samples, but it also flagged 20% of benign files as malicious. The team is concerned about the high number of false positives overwhelming the SOC. Which metric should they focus on to evaluate and improve the model?

   • AF1-score
   • BAccuracy
   • CPrecision
   • DRecall
   Reveal Solution Discussion Select an answer first