AI-Augmented Security Operations
Integrate machine learning and language models into detection, triage and response, with measurable performance and accountable human oversight.
About this program
Security operations teams are adopting AI to cope with alert volume, speed up investigations and automate response. Used well, it extends analyst capacity. Used carelessly, it introduces silent errors, unreviewed actions and a new attack surface inside the SOC itself.
This program teaches SOC analysts and detection engineers to apply AI where it adds value and to keep people accountable for the outcome. Learners work in a simulated security operations environment, building ML-assisted detections, using an LLM to support triage and investigation, and designing automation with clear approval points.
Throughout, the program focuses on measurement: precision, drift and analyst override rates, so teams can show whether their AI tools are working. It covers Domain 4 of the IIAS Body of Knowledge in depth and aligns to the Detect and Respond functions of NIST CSF 2.0.
Who it is for
Intended for
- SOC analysts at all tiers
- Detection engineers and threat hunters
- Incident responders
- SOC managers evaluating or deploying AI tools
Recommended background
- Working experience in security operations, detection or incident response
- Familiarity with SIEM queries, alert triage and common log sources
- AI Security Fundamentals, or equivalent understanding of AI concepts
What you will be able to do
- Identify where AI adds value in detection, triage and response, and where it does not
- Build and tune an ML-assisted detection and evaluate its false positive rate
- Use an LLM to support alert triage and investigation while verifying its output
- Design response automation with defined human approval points
- Measure precision, drift and analyst override rates for AI tools
- Secure the AI tools used by the security team against misuse and manipulation
Curriculum
Seven self-paced modules that follow the flow of security operations, from detection through response to governance of the SOC's own AI tools. Six include a graded lab.
AI in the security operations centerOpportunities and limits
- Where AI helps across detection, triage, investigation and response
- Failure modes: hallucination, bias, drift and automation complacency
- Roles and accountability when AI supports analysts
ML-assisted detection engineeringFinding signal in volume
- Anomaly detection and classification for security data
- Feature selection from common log sources
- Combining ML detections with rule-based detections
- Evaluating detections against labeled data
LLM-supported triageFaster first response
- Summarizing and enriching alerts with an LLM
- Prompting for consistent, structured triage output
- Verifying LLM conclusions against evidence
AI-assisted investigation and threat huntingAnalyst in the lead
- Using AI to generate hypotheses and queries
- Correlating evidence across sources
- Documenting AI-assisted findings for review
Response automation with human approvalDeciding what to automate
- Classifying response actions by risk and reversibility
- Designing approval points and escalation paths
- Playbook design for AI-recommended actions
Measuring AI performanceEvidence that the tools work
- Precision, recall and false positive rates in practice
- Detecting model drift over time
- Tracking analyst override rates and their causes
- Reporting AI performance to SOC leadership
Securing the SOC's own AI toolingDefending the defenders
- Prompt injection through logs, tickets and alert data
- Access control and data exposure in SOC AI tools
- Monitoring and incident response for AI tool compromise
Graded lab exercises
All exercises run in a simulated security operations environment with realistic log data and alert queues. Each has defined objectives that are checked on completion.
Build and tune an ML-assisted detection
Train an anomaly detection model on authentication logs, tune its threshold and measure false positives.
Triage an alert queue with LLM support
Use an LLM to summarize and prioritize alerts, then verify each conclusion against the underlying evidence.
Investigate an incident with an AI assistant
Work through a multi-stage incident using AI-generated hypotheses and queries, and document the findings.
Design an automated playbook with approval points
Classify response actions by risk and build a playbook that requires analyst approval where needed.
Build an AI performance dashboard
Calculate precision, drift and override rates from historical data and present them for SOC leadership.
Detect manipulation of a SOC AI assistant
Identify injected instructions hidden in log and ticket data, and apply controls that contain them.
Body of Knowledge coverage
How deeply this program covers each domain of the IIAS Body of Knowledge.
| Domain | Coverage |
|---|---|
| 1AI threat landscape and adversarial ML | Introduced |
| 2Secure AI lifecycle | Introduced |
| 3LLM and agentic AI security | Applied |
| 4AI-augmented security operations | Core |
| 5AI governance, risk and compliance | Applied |
| 6AI assurance and evaluation | Introduced |
| 7Synthetic media and identity defense | Introduced |
Core: assessed in depth. Applied: practiced in exercises. Introduced: concepts and terminology.
On completion
Completing all modules, knowledge checks and graded labs gives you:
Program certificate
The IIAS Certificate in AI-Augmented Security Operations, with a unique ID for verification, listing the Body of Knowledge domains covered.
12 CE hours
12 continuing education (CE) hours recorded on completion, which other certifying bodies may accept under their own rules.
Membership eligibility
Eligibility to take the membership assessment, the second step of the membership pathway.
Continue your learning
Explore more IIAS training
Browse all programs, or see how completing a program leads to IIAS membership.
Get IIAS updates
AI Threat Lab advisories, briefing invitations, new training programs and Body of Knowledge editions, in one email list.
