AI Red Teaming

Priority 12 · in the launch sequence

LevelFoundation

PrerequisitesNone

StatusIn development

SpecificationDraft · not approved

EnrolmentNot yet open

01Overview

The entry point to offensive work: red-teaming methodology, scoping and AI-specific threat modelling.

Domain scope · ASO

Systematic red teaming of AI systems, from prompt injection to full-scope agent exploitation, including adversarial ML, model fingerprinting and purple teaming.

Intended for: Red team specialists, adversarial ML researchers, penetration testers

02Planned topics

Planned · outcomes published with the specification

Red-team methodology
Scoping
AI-specific threat modelling
MITRE ATLAS orientation

03Proposed case references

Source review pending

I-2

OpenAI/DeepSeek Model Distillation CampaignSource review · In review

I-5

Context AI/Vercel OAuth Supply Chain BreachSource review · In review

I-6

Adaptive AI Infrastructure CampaignSource review · In review

Proposed connection, subject to source review. The specific connection between each case and the course content is published with the approved specification.

04Assessment

Format, duration, passing score and practical component are published with the approved specification.

05Instructor

TBA

Announced when appointed

Instructors are practitioners appointed against a written standard for the ASO domain.

How faculty are appointed →

06Related courses

Next on the Red team practitioner pathOC-LLMPILLM Prompt Injection & Jailbreak Engineering In this domain · PractitionerOC-AIRFAI Recon & Model Fingerprinting In this domain · PractitionerOC-AMLAAdversarial ML Attacks: Evasion, Extraction & Inference

Prerequisite forOC-AIRF AI Recon & Model Fingerprinting PractitionerOC-AMLA Adversarial ML Attacks: Evasion, Extraction & Inference PractitionerOC-LLMPI LLM Prompt Injection & Jailbreak Engineering PractitionerOC-OAATT Offensive AI: Attack Tools & Techniques Practitioner

View all 9 planning codes in AI Security: Offensive & Red Teaming →

Interest registration opens later.

Notification rules and data handling are published before registration opens.

Request a team proposal

Quick factsDraft

Course code	OC-AIRT
Standard ID	Assigned at approval
Domain	ASO · AI Security: Offensive & Red Teaming
Level	Foundation
Status	In development
Priority	Priority 12
Prerequisites	None. OC-AISF is recommended.
Corpus source	I-2 · I-5 · I-6
Duration	To be confirmed
Delivery	To be confirmed
Pricing	To be confirmed
Session dates	To be confirmed
Instructor	Founding cohort — appointment pending
Specification	Draft · not yet issued

Official specification registerOC-AIRTSpecification not yet issued

Version —Last reviewed —

This course is in active development. Duration, pricing, session dates and instructor are published when confirmed. Proposed case references, framework references, syllabus, labs and assessment are drafts until the course specification is approved.