You can see it againUnder pressure people bring back shapes and positions long after the wording has gone.
Picture superiority · Shepard 1967, Standing 1973
EC-COUNCILEC-Council Certified Offensive AI Security Professional
The EC-Council Certified Offensive AI Security Professional (COASP) certification validates your ability to red-team AI systems, exploit vulnerabilities in LLMs and agents, and build defenses that survive real-world attacks. It is designed for offensive security professionals who need to master prompt injection, data poisoning, and model manipulation. Earning COASP proves you can simulate attacks, find vulnerabilities, and harden AI systems before attackers exploit them.
Exam formatMultiple choice and performance-based
DeliveryPearson VUE
Free questions1198
Content last reviewed 30 July 2026 · Up to date
The certification
What EC-Council Certified Offensive AI Security Professional proves, and what it asks of you
What this certification covers, who it is written for, and what the exam itself looks like on the day.
7domains
28objectives
174concepts
US $1,699exam fee
What it is
What this certification is
What it validates, who it is written for, and the experience it assumes.
About this certification
The EC-Council Certified Offensive AI Security Professional (COASP) certification is the first AI security credential built specifically for AI red teamers. It equips you with a tactical methodology to hack LLMs and secure agentic AI, covering attack vectors such as prompt injection, data poisoning, and model theft. The program goes beyond traditional penetration testing, which does not address LLM-specific vulnerabilities, and provides a standardized approach to offensive AI security.
Through 10 comprehensive modules, you will master offensive techniques from reconnaissance to red teaming, including AI vulnerability scanning, adversarial machine learning, and AI incident response. You will learn to exploit AI agents, manipulate training pipelines, and attack AI infrastructure, while also building defenses that survive adversarial testing. The certification validates your ability to simulate attacks, find vulnerabilities, and harden AI systems, making you a valuable asset in the fight against AI-driven threats.
Who it’s for
This certification is for offensive security professionals, penetration testers, and AI security specialists who want to specialize in red-teaming AI systems. It is also ideal for security team members who need to understand and defend against LLM vulnerabilities, prompt injection, and data poisoning attacks. You should have a solid foundation in cybersecurity concepts and be comfortable with hands-on labs and attack methodologies. The program is designed for those who want to master the tactical skills needed to hack LLMs, break agents, and secure AI systems in real-world environments.
Recommended experience
EC-Council recommends hands-on experience in offensive security or penetration testing, with familiarity with AI/ML concepts and common attack frameworks. Experience with penetration testing methodologies and tools; Understanding of AI/ML fundamentals and LLM architectures; Familiarity with OWASP Top 10 and MITRE ATLAS frameworks; Knowledge of web application security and API testing
The syllabus
What you’ll learn
Every domain and objective EC-Council measures, with the weight they carry on the exam.
The official EC-Council exam outline · checked 30 July 2026 · See the source
Offensive AI Foundations and Hacking Methodology
- AI and machine learning fundamentals from an offensive security perspective
- AI attack surfaces, threat landscapes, and adversary techniques (MITRE ATLAS-aligned)
- AI system hacking methodologies, frameworks, and risk implications
- AI attack taxonomies and classification models
- OWASP LLM and ML Top 10 (2025) mapping to AI threat and governance
AI Reconnaissance and Vulnerability Discovery
- AI Reconnaissance and Attack Surface Mapping
- API Reconnaissance and model fingerprinting
- AI Vulnerability Scanning and Fuzzing
Prompt Injection and LLM Application Attacks
- Prompt injection attacks
- LLM jailbreaking
- RAG poisoning attacks
- Cross-LLM attacks
Adversarial Machine Learning and Model Privacy Attacks
- Adversarial machine learning techniques
- FGSM and PGD attacks on image classifiers
- Model extraction and theft
- Model privacy attacks
Data Pipeline and Agentic AI Attacks
- Data and training pipeline attacks
- Training data poisoning
- Agentic AI and model-to-model attacks
- Agent hijacking
AI Infrastructure and Supply Chain Attacks
- Authentication weaknesses in AI model APIs
- Parameter manipulation
- SSRF through AI tool calls
- Misconfigured cloud AI services (AWS Bedrock, Azure OpenAI, Google Vertex AI)
Security Testing, Hardening, and Incident Response
- AI Security Testing, Evaluation, and Hardening
- AI Incident Response and Forensics
- Scoping an AI red team exercise and threat modeling
- Professional AI red team reporting
On the day
The exam itself
Everything EC-Council publishes about sitting it, and nothing we inferred.
Prerequisites
No mandatory prerequisites — this certification has no required predecessor exam or credential.
CertificationEC-Council Certified Offensive AI Security Professional
Exam formatMultiple choice and performance-based
DeliveryPearson VUE
LanguagesEnglish
PricingUS $1,699
Certification levelProfessional
After you pass
Where this credential goes next
The path EC-Council lays out, how the credential is kept, and where to book.
Step-by-step path to EC-Council Certified Offensive AI Security Professional
Credential earnedEC-Council Certified Offensive AI Security Professional Professional level certification Renewal and maintenance
EC-Council certifications require renewal through continuing education credits. Specific renewal requirements for COASP are not yet published. Stay current with the latest technologies and maintain your certification.
Learn more about renewal requirements Lifecycle status
This certification is currently active and available. EC-Council maintains this certification to validate current skills and industry relevance.
Exam status: ActiveMaintained by EC-Council
Exam registration
Register for the exam through Pearson VUE, EC-Council’s authorized testing partner.
Schedule your examVisit the official EC-Council certification page for exam policies and requirements.
View the official pageYour coach
And when you are serious, your coach Pip takes over
Your coach in the app reads what you have answered with the book closed and tells you one thing to do tonight. It will not count an answer you gave with the page open, and it will tell you when you are not ready.
See how the coach worksBefore you book
Questions people ask
How is COASP different from traditional penetration testing certifications?
COASP is the first AI security certification built specifically for AI red teamers. Traditional pentesting does not cover LLM vulnerabilities like prompt injection, data poisoning, and model manipulation. COASP provides a standardized offensive AI security methodology and covers attack frameworks like OWASP LLM Top 10 and MITRE ATLAS.
Is there a hands-on lab component in the COASP training?
Yes, the COASP certification course includes hands-on labs. The course outline states that you will master offensive AI security from reconnaissance to red teaming with hands-on labs, covering attack methodologies, vulnerability exploitation, and incident response.
What job roles does the COASP credential map to?
The COASP credential is designed for AI red teamers, offensive security professionals, and penetration testers who specialize in AI systems. It validates skills in simulating attacks, finding vulnerabilities, and hardening AI systems, making it relevant for roles such as AI security specialist, red team operator, and offensive AI researcher.
Can I take the COASP exam without prior AI security experience?
EC-Council does not publish mandatory prerequisites for COASP. However, the course is designed for offensive security professionals, and the curriculum assumes familiarity with penetration testing concepts. Prior experience with AI/ML is recommended but not explicitly required.
What is the launch date for the COASP program?
The COASP program launches on 15 March 2026. Early sign-up is available now, and you can register early to be the first to get access.
Does COASP cover both attacking and defending AI systems?
Yes, while COASP focuses on offensive techniques, it also includes building defenses that survive adversarial testing. The curriculum covers AI security testing, evaluation, and hardening, as well as AI incident response and forensics, ensuring you can both break and secure AI systems.
Information freshness · Content last reviewed on 2026-07-30 Up to date
Practice free questions 1198 questions, free, no account needed.
The curriculum
The whole exam, mapped and written
Every domain, every objective, and every concept EC-Council measures — each one written out.
7domains
28objectives
174concepts
252free pages
The domains, and what sits inside them
Every objective below is a page you can open and practise now, without an account.
The official EC-Council exam outline · checked 30 July 2026 · See the source
1Offensive AI Foundations and Hacking Methodology217 questions
AI and machine learning fundamentals from an offensive security perspective5 concepts · 9 pagesOpen →AI attack surfaces, threat landscapes, and adversary techniques (MITRE ATLAS-aligned)6 concepts · 10 pagesOpen →AI system hacking methodologies, frameworks, and risk implications3 concepts · 9 pagesOpen →AI attack taxonomies and classification models5 concepts · 8 pagesOpen →OWASP LLM and ML Top 10 (2025) mapping to AI threat and governance6 concepts · 10 pagesOpen →
2AI Reconnaissance and Vulnerability Discovery137 questions
3Prompt Injection and LLM Application Attacks163 questions
4Adversarial Machine Learning and Model Privacy Attacks156 questions
5Data Pipeline and Agentic AI Attacks184 questions
6AI Infrastructure and Supply Chain Attacks151 questions
7Security Testing, Hardening, and Incident Response190 questions
Not a table of contents
Every line on this map already opens
In front of every objective the practice pages are already there, free and without an account. This is one objective, opened.
AI and machine learning fundamentals from an offensive security perspective9 pagesOpen →
Free in front of it
41 questions on this objective, five to a page. Every range above is a real page, open now, with no account.
Reading the map is not the same as knowing the ground
The curriculum tells you what is on the exam. Proving you know it is a different job — and it is the one the closed-book run does.
Free questions
1198 questions. No account, no card.
The whole bank is open. 5 questions to a page, every answer explained, and a discussion thread on each one.
1198questions
252pages
28objectives
Freealways
Start anywhereAI and machine learning fundamentals from an offensive security perspective 41 questions · 9 pages
Browse by domain
Every objective, and every page range, is a link — so you can pick up exactly where you left off.
1Offensive AI Foundations and Hacking Methodology217 questions
2AI Reconnaissance and Vulnerability Discovery137 questions
3Prompt Injection and LLM Application Attacks163 questions
4Adversarial Machine Learning and Model Privacy Attacks156 questions
5Data Pipeline and Agentic AI Attacks184 questions
6AI Infrastructure and Supply Chain Attacks151 questions
7Security Testing, Hardening, and Incident Response190 questions
What a practice page gives you
1Five to a page
Short enough to finish, long enough to matter.
2Every answer explained
Not only which one is right — why the others are wrong.
3A discussion on each
Ask, answer, and vote. Every question has its own thread.
A question, and the idea behind it
Every question comes from a concept
These are not trivia. Each one is written against a concept in the book, so when you get one wrong there is somewhere to go and find out why.
The visual book
See it once. Carry it into the exam.
The pages shown here come from our AI-900 book — an example of how each concept is written in plain language and, where the idea needs one, drawn as a full page you can take in at a glance.
174concepts
1198free questions
Why a picture, and not another paragraph
Three reasons, and each one is a real finding rather than a slogan.
You can see it againThe whole idea at onceWhere it starts, what happens in the middle, what comes out, and the mistake to avoid.
Multimedia principle · MayerThe look-alikes sit togetherThe pairs the exam tests are drawn side by side, so the difference is seen, not told.
Dual coding · PaivioWhat one page is made of
You are never asked to read a poster here — only to see how one is built. After that, every other page is legible at a glance.
1A numbered strip on top
The idea as a sequence, followed with a finger before a word is read.
2Panels for the parts
What it is, how the machine learns it, when it is the right tool.
3The trap, framed
The distinction the exam tests, given its own box instead of buried in prose.
4One line at the bottom
The sentence to carry into the exam room.
Open book, on purpose
Answer it with the picture beside you
This is the part that teaches. The illustration and the written explanation stay where they are while you work, so a scenario stops being a memory test and becomes something you can simply look at.
It teaches · it does not count
A smartphone uses AI to unlock when the owner looks at the camera. Which AI capability is being used?
AImage classification
BFacial recognition
COptical character recognition
DObject detection
Look at the five steps. Detect finds a face, align straightens it, encode turns it into numbers, search compares it with a stored face, and decide answers one question: is this the same person? Classification would only say “a face”. Detection would only draw a box. Neither decides whose.
Then the page shuts, and it starts counting
The same questions come back with the book closed — that run is the one that counts. After it, your coach picks one thing for tonight, sized to the time you have, and brings pages back before you lose them.
Testing effect · Roediger & Karpicke 2006 · spacing effect · Cepeda et al. 2006
Official resources
Straight from EC-Council
Where the exam is defined, scheduled and scored.
2official links
174concepts mapped
The source
EC-Council’s own pages
We link to them rather than repeat them, so nothing here goes stale behind them.
Checked against the source
Every objective on the official EC-Council outline already has questions here
We build from the official skills outline, not from a summary of it — 28 objectives, 174 concepts written under them, and free questions against every one. When EC-Council changes the outline, this page changes with it.
28objectives on the outline→174concepts written→1198free questions
An official page tells you what will be asked. It cannot tell you what you will get right.
That is the only question worth answering the night before, and no link answers it. You answer it by taking the questions with the book closed, and seeing what comes back.