5-Day Instructor-Led Programme
The XAIHP Certification Programme is the practitioner standard for offensive security professionals who assess, test, and attack AI systems including LLMs, RAG pipelines, agentic architectures, and AI supply chains. Assessed on Day 8 through a supervised AI red team engagement against a realistic enterprise AI deployment — no multiple choice, no exam, no question bank.
Duration
5 Days
Price
$6,244
AI systems are now inside every enterprise , processing sensitive data, making autonomous decisions, and connecting to production infrastructure. The attack surface they create is vast, poorly understood, and almost entirely uncovered by traditional penetration testing. XAIHP is the first UK instructor-led certification programme built specifically for professionals who want to assess AI systems offensively and report findings to enterprise and regulatory standards.
Across eight days, participants build practical skills across the full AI attack surface: LLM prompt injection, jailbreaking, guardrail bypass, RAG pipeline poisoning, agentic AI exploitation via MCP, adversarial machine learning attacks, AI supply chain compromise, and structured AI red team operations. Every session uses real AI deployments, current attack tooling, and real enterprise scenarios , no theoretical slides.
On Day 8, participants conduct a structured AI red team engagement against a simulated enterprise environment including a deployed LLM, a RAG pipeline, and an agentic workflow. A Practitioner Assessment Report is issued with the XAIHP certificate. Aligned with OWASP LLM Top 10 2025, MITRE ATLAS, NIST AI RMF, EU AI Act 2024, and ISO/IEC 42001.
Hands-on prompt injection, jailbreaking, RAG pipeline poisoning, agentic AI exploitation via MCP servers, adversarial ML attacks, and AI supply chain assessment against real AI deployments.
Mentor-led sessions mapping AI attacks to MITRE ATLAS and OWASP LLM Top 10 2025, and contextualising findings within EU AI Act 2024 and NIST AI RMF regulatory obligations.
Conduct authorised AI red team engagements across LLMs, RAG pipelines, and agentic systems, and produce professional assessment reports that meet enterprise and regulatory standards.
Design and execute structured AI red team engagements against LLMs, RAG pipelines, and agentic AI systems using MITRE ATLAS methodology
Analyse AI deployment architectures to identify attack surfaces and map vulnerabilities to OWASP LLM Top 10 2025
Implement prompt injection, jailbreaking, and guardrail bypass techniques against production AI systems in authorised environments
Evaluate AI supply chain integrity including model repositories, training pipelines, MCP servers, and inference infrastructure
Conduct adversarial machine learning assessments covering evasion, poisoning, and model extraction techniques
Produce professional AI red team reports aligned to NIST AI RMF and EU AI Act regulatory requirements
Minimum 12 months in a cybersecurity, software engineering, or data engineering role
Basic understanding of how AI and LLM systems function at a conceptual level — deep ML expertise is not required
Familiarity with API testing concepts and at least one scripting language (Python preferred)
Organized by professional domains with comprehensive coverage
Master these in-demand skills through hands-on practice
A clear view of the roles this programme supports, what typically comes next, and where learners progress over time
Typical next step: XAIG (AI Governance Practitioner) for the regulatory governance dimension, or XEHP for broader traditional penetration testing capability.
Choose the learning format that works best for you and your team
Instructor-Led Training
Join live instructor-led sessions from anywhere. Interactive, engaging, and flexible.
Price per person
Group enrolments and early planning options available.
Custom quotes for teams and organisations
We come to you. Training delivered at your workplace for teams of 6 or more.
Custom pricing based on:
No obligation. Response within 1 business day.
Classroom training at a professional venue. Ideal for focused, immersive learning.
Custom pricing based on:
No obligation. Response within 1 business day.
Combine online and in-person learning for maximum flexibility and impact.
Timeline tailored to learner availability
Custom pricing based on:
No obligation. Response within 1 business day.
All prices are exclusive of VAT where applicable. Group enrolments and custom packages available on request.
Not everyone learns best in a group. If you want focused guidance, faster clarity, and confidence you can use on the job, our 1-to-1 Fast-Track Training gives you private, mentor-led support tailored to your experience and goals.
"Many learners choose 1-to-1 when they want understanding, not memorisation."
Credential
On successful completion of XAIHP — Xcademia AI Hacker Practitioner , learners receive an Xcademia Certificate of Completion. This standalone certificate is issued directly by Xcademia and recognised by employers across the UK defence and security sector.
Everything you need to know about the certification exams
You will receive an Xcademia certificate of completion based on participation and successful completion of labs and scenario simulations.
Everything you need to know about this course
COASP launched February 2026 as an MCQ exam. XAIHP is 8 instructor-led days ending in a supervised AI red team engagement against real AI systems. There is no comparable instructor-led AI hacking programme in the UK market. XAIHP is the first — and currently the only — practitioner-assessed AI hacking certification in the UK.
Take the next step in your professional development