AI Security workshop
Hands-On LLM Red-Teaming
Attack your own GenAI application, find what breaks, and keep the attacks as tests.
- 2 days
- Hands-on in AI Governance Platform
- On your own system
The problem
A GenAI app that has never been attacked will be. This workshop red-teams your application with manual and automated attacks, then turns the findings into a regression suite.
Who it's for
AppSec, security engineering, and the developers who own the GenAI application.
What to bring
A test environment of your GenAI app and its system prompt and tool list.
The course side
What your team learns
- 1
Threat model
Assets, trust boundaries, tools, and data paths of your system.
- 2
Manual attacks
Jailbreaks, prompt injection, data exfiltration, and abuse of tools.
- 3
Automated attack simulation
Scaled attacks with PyRIT, scored for success.
- 4
Findings to fixes
Each finding mapped to a guardrail, a prompt change, or a monitoring rule.
Builds on these course lectures
- Generative AI Red Teaming Challenge
- GenAI Attacks & Defenses
- Leveraging Red Teaming for AI Governance
The platform side
What your team builds in AI Governance Platform
- Build the threat model for your application
- Log every red-team finding as a scored risk with an owner
- Track each fix as a control and re-test it
Also used: PyRIT, OWASP LLM Top 10 test cases, Promptfoo red-team
About AI Governance Platform →Your team leaves with
- • Red-team findings ranked by severity
- • A reusable attack regression suite
- • A remediation plan
Book this workshop
Request Hands-On LLM Red-Teaming
It's pre-selected in the form. Add others to combine them. Contact us for pricing: fill in your details and we'll reply within one business day.
Often combined with
- Prompt Injection & Data Leakage Defense · 1 day
- Securing AI Agents · 1 day