GenAI and LLM Application Security
This advanced course in Toronto is for the people responsible for shipping a generative AI product safely. It goes deep on application security for large language model (LLM) systems, from prompt security architecture through model supply chain to deployment.
You will design guardrails and then evaluate whether they work, secure agent frameworks against excessive agency, and build secure deployment patterns for AI features. It assumes you already understand the fundamentals and want production-grade depth.
- Duration
- 10 weeks
- Format
- Live online, instructor-led
- Prerequisites
- Building and Securing RAG and Agentic AI Systems
- Class size
- Capped at 12 learners
What you will be able to do
- Design a prompt security architecture for a real application
- Evaluate a guardrail with data rather than assertion
- Secure the model supply chain from source to serving
- Harden an agent framework against excessive agency
- Apply secure deployment patterns for AI in production
- Lead a security review of a generative AI application
- Map controls to recognized AI security frameworks
Course outline
6 modules
- Separating trusted instructions from untrusted input
- System prompt design and its limits
- Context construction and injection surfaces
- Defence in depth around the model
What you need before you start
- You have completed Building and Securing RAG and Agentic AI Systems or equivalent
- You are an experienced developer or application security engineer
- You are comfortable with Python and with cloud deployment concepts
- You have shipped or reviewed a production application before
Who this course is for
- Application security engineers responsible for AI products
- Senior developers and architects building generative AI at scale
- Platform teams providing AI capabilities to other teams
- Security leads who must sign off on an AI launch
Where this leads
Prepares you for
CSSLP
Awarded by ISC2
This course strengthens the secure software practices assessed by the ISC2 CSSLP, applied to generative AI systems. CSSLP is awarded by ISC2 after their exam and experience requirements, not by the academy; the course develops the AI-specific side of that secure development discipline.
Questions about this course
More in ai security
CoreAI Security Principles and Practices: GenAI and LLM Defence
The foundational AI security course: threat model generative AI, defend against prompt injection, and set pragmatic policy for an enterprise rolling out AI.
8 weeks · live online
Contact for pricingView outline
CoreBuilding and Securing RAG and Agentic AI Systems
Build retrieval augmented generation and agentic AI hands on, then secure them: indirect injection, vector store isolation, and constrained agent tools.
8 weeks · live online
Contact for pricingView outline
CoreAdversarial AI: Penetration Testing AI Systems
Penetration test AI systems themselves: model attacks, jailbreak methodology, data extraction, and reporting findings that are probabilistic, not binary.
6 weeks · live online
Contact for pricingView outline
Ready to launch your cyber security career?
Join the next live online cohort. No experience required, just bring the curiosity.