Wirewalk Instituteof AI
sec-310 Expert Available

AI Red Teaming

For experienced security testers and AI engineers who plan, run and report authorized red team engagements against LLM applications, agents and the systems around them.

Level
Expert
Study time
20 hours
Lessons
19 in 6 modules
Exam
25 questions

About this course

AI red teaming borrows the discipline of traditional red teaming but adds targets that are probabilistic, conversational and connected to tools. This course teaches you to run engagements that produce findings developers can fix and leaders can trust. It starts with scope: separating security testing from safety and misuse evaluation, obtaining written authorization, and setting rules of engagement for systems that may touch production data or take real actions. Planning is threat-informed, using MITRE ATLAS (v2026.09 at review, 16 tactics) and the OWASP Top 10 lists for LLM and agentic applications.

You will work through jailbreak families, indirect injection and exfiltration chains, retrieval manipulation and corpus poisoning, and tool and agent abuse. You will automate with PyRIT, garak and promptfoo, use attacker models and multi-turn strategies such as PAIR, TAP and Crescendo, and score results with classifiers, LLM judges and human review. The course extends beyond the prompt to model-level testing, APIs, serving infrastructure and multimodal inputs, then covers attack success rates with confidence intervals, actionable reporting and coordinated disclosure. It closes with continuous red teaming in CI, building the team, and a capstone engagement against a hypothetical agentic application. All techniques are taught for authorized testing of systems you are permitted to assess. The Wirewalk Institute certificate attests to completion and assessment of this course; it is not endorsed by OWASP, MITRE, NIST or any vendor named here.

What you will be able to do

  • Scope an AI red team engagement with written authorization, rules of engagement and safe handling of production data
  • Build a threat-informed test plan from MITRE ATLAS and the OWASP LLM and agentic lists
  • Execute jailbreak, indirect injection, retrieval manipulation and agent abuse test cases end to end
  • Automate multi-turn attacks with PyRIT, garak or promptfoo and score results reliably
  • Report attack success rates with sampling and confidence that reflect non-deterministic behavior
  • Write findings with reproduction steps, severity and root cause that lead to architectural fixes
  • Design a continuous AI red teaming program integrated with the release process

Syllabus

6 modules · 19 lessons · about 20 hours

Module 1: Scope, Authorization and Planning

What AI red teaming covers and how to plan an engagement you are permitted to run.
3 lessons
  1. Security, Safety and Misuse Testing: Defining What You Are Testing
  2. Scoping, Authorization and Rules of Engagement for AI Targets
  3. Threat-Informed Planning with MITRE ATLAS and the OWASP Lists

Module 2: Attacking LLM Applications and Agents

Core attack techniques against the application layer.
4 lessons
  1. Jailbreak Families and Why They Work
  2. Indirect Injection and Exfiltration Chains End to End
  3. Attacking Retrieval: Ranking Manipulation and Corpus Poisoning
  4. Abusing Tools and Agents: From Injected Text to Real Actions

Module 3: Automation at Scale

Harnesses, attacker models and scoring.
3 lessons
  1. Red Teaming Harnesses: PyRIT, garak and promptfoo
  2. Attacker Models and Multi-Turn Strategies: PAIR, TAP and Crescendo
  3. Scoring Results: Classifiers, LLM Judges and Human Review

Module 4: Beyond the Prompt

Testing the model, the platform and non-text inputs.
3 lessons
  1. Model-Level Testing: Extraction, Inversion and Evasion in Scope
  2. Testing the Surrounding System: APIs, Identity, Serving and Supply Chain
  3. Multimodal and Voice Interfaces

Module 5: Measurement and Reporting

Turning probabilistic results into defensible findings.
3 lessons
  1. Attack Success Rate, Sampling and Statistical Confidence
  2. Writing Findings Developers Can Fix: Reproduction, Severity and Root Cause
  3. Coordinated Disclosure for AI Vulnerabilities

Module 6: Running an AI Red Team Program

Continuous testing, team design and a capstone engagement.
3 lessons
  1. Continuous Red Teaming in CI/CD
  2. Building and Staffing an AI Red Team
  3. Capstone: A Full Engagement Against a Hypothetical Agentic Application

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 MITRE ATLAS, OWASP, Microsoft PyRIT, NVIDIA garak, or Promptfoo. Product and company names are trademarks of their respective owners.

More in AI Security: Securing AI Systems

All 13 courses in this track
sec-001 Free intro Available

Using AI Safely at Work: The Essentials

Follow one fictional US distributor through four everyday AI mistakes (a guarantor's credit file uploaded to a personal account, a customer letter promising a fee waiver that does not exist, a vendor email with hidden instructions for the assistant, and a note-taker that sent a customer the internal margin floor) and practice the decisions that prevent or contain each one in three short Decision Labs.

1 h · 7 lessons Free intro
sec-101 Basic Available

Using AI Safely: Data Handling for Every Employee

A plain-language course on handling data safely with AI tools: what happens to what you type or upload, how to classify before you paste, how connected apps and agents change the picture, and how to report a mistake quickly.

6 h · 15 lessons See price at checkout
sec-201 Intermediate Available

AI Security Fundamentals: The OWASP Top 10 for LLMs

A practitioner course on securing applications that use large language models, organized around the 2026 OWASP Top 10 for LLM Applications. Every risk comes with a hypothetical scenario, the root cause, and concrete defenses in code and configuration.

14 h · 18 lessons See price at checkout