For identity security, fraud and detection teams who use behavioral analytics and machine learning to catch account takeover, insider risk and fraud, and need to tune and explain those models.
The curriculum is being prepared and reviewed. Enrollment is not open yet.
About this course
Stolen credentials and session tokens are among the most common ways in, and fraud teams face the same problem: the attacker looks like a legitimate user. Behavioral analytics and machine learning are the main tools for telling them apart, and they generate a lot of noise when poorly tuned. This course explains how these systems work so you can deploy, tune and defend them.
You will study identity attack patterns (password spraying, MFA fatigue, adversary-in-the-middle phishing, token theft and consent abuse) and how identity threat detection works in products such as Microsoft Entra ID Protection, Okta and CrowdStrike Falcon Identity Protection. You will build baselines and peer groups, compare statistical and machine learning anomaly detectors in Python with scikit-learn and PyOD, apply graph analytics to fraud rings and lateral movement, and learn how risk-based authentication and step-up decisions use model scores. The course places heavy weight on operations: precision at a fixed alert budget, feedback loops, concept drift, explaining an alert to an analyst, and the privacy and employment-law care that insider risk monitoring requires. Product details are reviewed as of October 2026.
What you will be able to do
Describe modern identity attack techniques and the signals that reveal them
Build user and entity baselines and peer groups and choose features that separate attackers from unusual but legitimate users
Implement and compare statistical and machine learning anomaly detectors on authentication and transaction data
Apply graph analytics to detect fraud rings, shared infrastructure and lateral movement
Tune detectors to a fixed alert budget and manage drift and analyst feedback
Explain an anomaly alert to an analyst or customer with interpretable evidence
Design insider risk and fraud monitoring with proportionate privacy and legal safeguards
Syllabus
5 modules · 15 lessons · about 12 hours
1
Module 1: Identity Attacks and Their Signals
What account takeover and token abuse look like in logs.3 lessons
Password Spraying, MFA Fatigue and Adversary-in-the-Middle Phishing
Token Theft, Session Hijacking and OAuth Consent Abuse
Identity Threat Detection and Response Products Compared
2
Module 2: Baselines, Peer Groups and UEBA
Model normal behavior so abnormal behavior stands out.3 lessons
Feature Engineering from Authentication and Access Logs
Peer Groups and Entity Baselines
Impossible Travel and Why It Fails Naively
3
Module 3: Anomaly Detection Methods
Hands-on comparison of detectors on realistic data.3 lessons
Statistical Baselines Versus Isolation Forest and Autoencoders
Graph Analytics for Fraud Rings and Lateral Movement
Evaluating Detectors with Precision at a Fixed Alert Budget
4
Module 4: Fraud and Risk-Based Decisions
Use model scores to drive authentication and transaction decisions.3 lessons
Transaction and Account Fraud Models
Risk-Based Authentication and Step-Up Policies
Feedback Loops, Label Delay and Concept Drift
5
Module 5: Operating and Explaining Detections
Make alerts actionable and keep monitoring proportionate.3 lessons
Explaining an Anomaly Alert with Interpretable Evidence
Using LLMs to Summarize Identity Investigations
Insider Risk Monitoring: Privacy, Proportionality and Legal Care
Exam and certificate
The exam unlocks once you have completed every lesson. It draws 20 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 45 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.
Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.
The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by Microsoft, Okta, CrowdStrike, Splunk, Google, scikit-learn, or PyOD. Product and company names are trademarks of their respective owners.
Learn what generative AI has changed about scams, from cloned voices and deepfake video calls to fluent phishing, and build a short set of verification habits that work no matter how convincing the fake is. Free, about one hour, with a 10-question check at the end.
A plain-language introduction to AI in cyber defense: the difference between classic machine learning detection and LLM assistants, where each shows up across the security stack, how attackers are using AI, and how to judge a security AI claim. No coding or security background beyond IT basics is required.
Practical rules for using general-purpose and security-specific AI assistants in security work: classifying what can be shared, sanitizing logs and malware samples, verifying output before acting, handling untrusted content that may carry prompt injection, and keeping an auditable record. Ends with a one-page team policy you can adopt.