For cloud security and network security engineers who analyze large volumes of cloud audit logs, flow records and network metadata, and want AI to find threats and misconfigurations at that scale.
The curriculum is being prepared and reviewed. Enrollment is not open yet.
About this course
Cloud and network telemetry is high-volume and mostly benign, which makes it a natural target for machine learning and a hard place to get signal. This course teaches how to turn that data into detections and investigations, using both the managed AI-driven services the cloud providers offer and analytics you build yourself.
You will start with the data: AWS CloudTrail, Azure activity and Entra logs, Google Cloud audit logs, VPC and network flow logs, Kubernetes audit logs, and network metadata from Zeek and Suricata, normalized into a security data lake with OCSF (for example via Amazon Security Lake) or your SIEM's schema. You will evaluate what managed services such as Amazon GuardDuty, Microsoft Defender for Cloud and Google Security Command Center detect with ML, and where you still need custom analytics. Hands-on modules cover anomaly detection on control-plane API activity and flows, beaconing and DNS tunneling detection, encrypted-traffic analysis with JA4-style fingerprints and flow features, graph-based attack-path analysis combining posture and identity data as in cloud-native application protection platforms such as Wiz, and LLM-assisted investigation of cloud incidents that turns raw API sequences into readable narratives. The course ends with cost-aware architecture and detection coverage mapped to the ATT&CK Cloud and Containers matrices. Service details are reviewed as of October 2026.
What you will be able to do
Collect and normalize cloud audit, flow, Kubernetes and network metadata into a security data lake using OCSF or an equivalent schema
Evaluate managed AI-driven cloud threat detection services and identify the gaps that need custom analytics
Build anomaly detectors for cloud control-plane activity and network flows with realistic false-positive budgets
Detect beaconing, DNS tunneling and suspicious encrypted traffic using flow features and fingerprints
Use graph-based attack-path analysis that combines posture, identity and network reachability
Investigate cloud incidents with LLM assistance that turns API call sequences into verified narratives
Design a cost-aware cloud and network analytics architecture with coverage mapped to MITRE ATT&CK
Syllabus
6 modules · 17 lessons · about 20 hours
1
Module 1: Cloud and Network Security Data
What telemetry exists, what it costs and how to normalize it.4 lessons
Cloud Audit Logs: CloudTrail, Azure Activity and Entra, Google Cloud Audit Logs
Flow Logs, Zeek and Suricata Network Metadata
Kubernetes Audit Logs and Container Runtime Telemetry
Security Data Lakes and OCSF Normalization
2
Module 2: Managed AI-Driven Cloud Detection
What the providers detect for you, and what they miss.2 lessons
Amazon GuardDuty, Microsoft Defender for Cloud and Google Security Command Center
Finding Coverage Gaps Against ATT&CK Cloud and Containers Matrices
3
Module 3: Control-Plane Analytics
Detect misuse of cloud APIs and identities.3 lessons
Anomaly Detection on API Call Patterns and Identities
Detecting Credential Abuse and Privilege Escalation in the Cloud
Tuning to an Alert Budget Across Many Accounts and Subscriptions
4
Module 4: Network Analytics
Find command-and-control and exfiltration in network data.3 lessons
Beaconing and Periodicity Detection
DNS Tunneling and Domain Generation Detection
Encrypted Traffic Analytics with Flow Features and JA4-Style Fingerprints
5
Module 5: Attack Paths and Investigation
Connect posture, identity and reachability, and investigate with AI help.3 lessons
Graph-Based Attack-Path Analysis in Cloud Environments
LLM-Assisted Cloud Incident Investigation
Verifying AI Narratives Against Raw API Events
6
Module 6: Architecture and Operations
Build analytics that scale and stay affordable.2 lessons
Cost-Aware Pipeline Design for High-Volume Telemetry
Detection-as-Code and Coverage Reporting for Cloud and Network
Exam and certificate
The exam unlocks once you have completed every lesson. It draws 25 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 60 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 AWS, Microsoft, Google, Zeek, Suricata, OCSF, Wiz, Elastic, or Splunk. 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.