SC-100 Practice Question: Design security operations, identity, and compliance capabilities
Your organization uses Microsoft Sentinel as a SIEM. You need to design a solution to detect advanced persistent threats (APTs) by correlating data from multiple sources, including network logs, endpoint data, and threat intelligence feeds. The solution must use machine learning to identify anomalies and reduce false positives. Which analytics rule type should you configure?
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Fusion
Fusion analytics rules in Microsoft Sentinel are specifically designed for advanced multistage attack detection, using machine learning to correlate alerts and signals from multiple sources (network logs, endpoint data, threat intelligence) into high-fidelity incidents, which matches the APT detection and false-positive reduction requirement. ML Behavior Analytics rules focus on specific user/entity behavior anomalies rather than cross-source APT correlation. Anomaly detection rules identify unusual behavior within a single data type and do not perform the multistage fusion correlation. Scheduled query rules run KQL queries on a schedule and lack the built-in ML-driven cross-source correlation for APTs.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
ML Behavior Analytics
Why it's wrong here
ML Behavior Analytics is not a recognized analytics rule type within Microsoft Sentinel. Sentinel’s rule types include Scheduled, Microsoft Security, Fusion, and Anomaly; 'ML Behavior Analytics' appears to conflate machine learning with behavioral analytics but does not correspond to any selectable rule template. Therefore it is incorrect because it is not an actual rule category, unlike Fusion which is a genuine ML-based rule.
- ✓
Fusion
Why this is correct
Fusion is a built-in analytics rule in Microsoft Sentinel that leverages machine learning to correlate security alerts from multiple products—such as Microsoft Defender for Endpoint, Defender for Identity, and Defender for Office 365—into a single incident. It is specifically designed to detect advanced multi-stage attacks, including APTs, by analyzing cross-source alert relationships and timestamps. This makes Fusion the correct answer because it uniquely uses ML for multi-source correlation and APT detection.
- ✗
Anomaly detection rules
Why it's wrong here
Anomaly detection rules in Sentinel are a distinct rule type that applies machine learning to a single data source to identify unusual patterns, such as spikes in sign-in failures from one user. Unlike Fusion, these rules operate independently per source and do not correlate alerts across multiple security products. They are wrong for this question because they lack the multi-source correlation that is essential for detecting APTs, which Fusion provides.
- ✗
Scheduled query rules
Why it's wrong here
Scheduled query rules are deterministic and rely on KQL (Kusto Query Language) queries that run on a defined schedule to match specific event patterns or exclusions. They do not incorporate machine learning and cannot intelligently correlate alerts from different sources; instead, they simply return raw results based on the query logic. These rules are incorrect for the question because they are rule-based rather than ML-driven, while Fusion specifically combines ML with cross-source alert correlation.
Go deeper
Related to this question
About these practice questions
One of 605 original SC-100 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This SC-100 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the SC-100 exam.