Certified AI Security Champion

About This Course

Certified AI Security Champion is a one-day, hands-on introduction to attacking and defending AI systems. Instead of walking through a list of vulnerabilities, the course is organised around the six places an LLM actually shows up in a modern application: LLM-enabled apps, RAG pipelines, memory, agents and tools, the Model Context Protocol (MCP), and Agent Skills. For each one, you will run a real attack in a lab, then turn around and build the defense that stops it.

The course uses the AppSecEngineer platform with live models and pre-built environments, so all you need is a browser. Once the training is complete, you take a separate 24-hour Capture-the-Flag (CTF) certification exam, which you can start any time within a year of the course. Pass it, and you earn the Certified AI Security Champion credential.

Your Top 4 Takeaways

1. Think in contexts, not just vulnerabilities.
   Learn to recognise the six LLM contexts (apps, RAG, memory, agents and tools, MCP, Agent Skills) in any architecture and map the attack surface each one introduces.
2. Attack every context hands-on.
   Execute prompt injection, system prompt leakage, vector poisoning, memory poisoning, excessive agency, MCP misconfiguration, and malicious skill attacks against live systems in guided labs.
3. Defend every context with something you can ship.
   Leave with working patterns for output handling, retrieval trust controls, memory scoping, tool allow listing, MCP gateway hardening, skill review, semantic guardrails, and automated red-teaming with Promptfoo and Vigil.
4. Get certified on your own schedule.
   Take the CTF exam after the course, when the material has settled, and earn a credential that reflects practical skill rather than attendance.
   
   

Who Should Attend

• Application Security Engineers and Analysts
• Software Engineers and Developers building AI features
• DevSecOps, DevOps, and Platform Engineers
• Security Architects and Security Engineers
• Cloud Security Engineers managing AI services
• Penetration Testers and Red Teamers expanding into AI targets
• Technical Product Managers and Engineering Leads who need to review AI designs
  
  

Why Should You Attend

• A clear mental model. Rather than memorising a top-ten list, you leave with a framework for reasoning about any AI feature: where the LLM sits, what it can read, what it can remember, what it can do, and what it trusts.
• Attack and defend, side by side. Every lab pair puts you on both sides of the same weakness, so the defense is never abstract.
• Coverage of what teams are actually building. RAG, memory, tool-using agents, MCP servers, and Agent Skills are the building blocks of today’s AI products, and this course treats each as a first-class topic.
• A credential you earn after the fact. Taking the exam after the course means the certification measures what stuck, not how tired you were at the end of the day.
  

Delivered by Abhay Bhargav

Abhay Bhargav is the Founder and Chief Research Officer of we45, a specialist application security company, and the creator of AppSecEngineer, an elite hands-on security training platform. He started his career breaking applications through penetration testing and red-teaming, and has spent the last 15+ years scaling application security across cloud-native, DevSecOps, and AI-powered environments.

A regular speaker and trainer at DEF CON, Black Hat, OWASP, and RSA Conference, Abhay’s training programmes have been sold-out events globally, including at Black Hat USA, AppSecUSA, CodeBlue Japan, and AppSecDay Melbourne. He is a member of the Forbes Technology Council and the author of two internationally published books: Secure Java: For Web Application Development and PCI Compliance: A Definitive Guide.

Run this course in-house

Informa Connect Academy’s customised training solutions have helped organisations deliver tailored learning in different languages to suit every requirement.

Certification Exam (After the Course)

Exam format: Capture-the-Flag (CTF) certification exam.

When: The exam is taken after the training, not during it. Exam access is issued on completion of the course and remains valid for one year, so you can revisit labs and start the exam whenever you are ready.

Where: Online, on the same AppSecEngineer platform used for the labs. No proctor or on-site attendance required.

Length: 24 hours, timed from the moment you start.

Structure:

• Challenges: 10–12 hands-on challenges, at least one per context (LLM enabled apps, RAG, memory, agents and tools, MCP, Agent Skills), ranging from easy (identify and exploit a prompt injection) to harder (chain an indirect injection through a tool call, or identify and fix a misconfigured MCPscope).
• Attack and defense balance: Roughly two-thirds of challenges are offensive (capture the flag); the remainder ask you to apply or select the correct defense for a given scenario.
• Scoring: Points-based. A score of 70% is required to pass.
• Reward: Successful candidates receive the Certified AI Security Champion certificate and a shareable digital credential badge.

Prerequisites

This is an introductory course. You need a basic understanding of how web applications work (requests, responses, APIs) and a general awareness of common security issues such as injection and access control.

Comfort reading short Python snippets is helpful but not required; labs are guided, and no code has to be written from scratch. No prior AI, machine learning, or LLM security experience is required. All core concepts, from tokens and prompts to agents and MCP, are introduced from scratch.

(All participants receive access to a cloud-based lab environment with all required tools, live LLM API access, and pre-built agent, RAG, and MCP environments. Bring a laptop with a modern web browser. No local setup or special hardware is needed.)

Ideal Years of Practical Experience

The course is designed for practitioners with 0–3 years of experience in application security, software engineering, DevOps, or a related technical role, as well as more experienced engineers who are new to AI systems.

Attendees should be comfortable using a browser-based lab environment and reading technical documentation. No prior machine learning or AI security experience is needed.