Abstract
Through this workshop, participants will learn what continuous red teaming means and how it can protect AI agents from security vulnerabilities like prompt injection, data leakages and business alignment failures like hallucinations, inappropriate denials, etc. We'll present how enterprises can automate security evaluation, detect vulnerabilities before they become incidents, and ensure continuous protection of AI agents. Through hands-on exercises aligned with Giskard Hub, attendees will explore a variety of testing techniques including context-specific prompts, adaptive probing, and multi-turn interactions.
Topics To Be Covered
Understand LLM vulnerabilities and how continuous AI red teaming prevents them
Learn how to protect AI agents from security vulnerabilities and business failures
Apply red teaming techniques from cybersecurity to ensure the security and reliability of your LLM application
Perfect For
Enterprise AI & Compliance Leaders
LLM & AI Engineers
Data Scientists
Regulatory & Governance Specialists
AI Security & Risk Management Teams
Meet Your Instructor
Jean-Marie John-Mathews
Co-CEO and Co-Founder, Giskard
Jean-Marie John-Mathews is the Co-CEO and co-founder of Giskard AI, a company focused on testing, evaluating, and securing AI systems. An AI safety researcher with a PhD from Université Paris-Saclay, his work explores explainable AI, fairness in machine learning, and the societal impacts of automated decision-making. Before founding Giskard in 2021, he worked at the intersection of data science, ethics, and public policy, including leading research initiatives at the Good In Tech academic chair and teaching quantitative methods, AI, and public policy at institutions such as Sciences Po and Université Paris-Dauphine. Jean-Marie is widely recognized for his research on AI risks—including misinformation, bias, and adversarial attacks—and for advancing practical tools and benchmarks that help organizations build safer and more trustworthy AI systems.
ADDITIONAL INFORMATION
Time & Place
Wed, March 25
09:15 - 09:45
The Ritz-Carlton Berlin
Salon Tiergarten
Classroom Seating
Max. Capacity: 32 Seats
Secure your seat – registration required.
Notes
Agenda for this session:
Getting Settled - 5 mins
Information Session - 40 mins
Break - 5 min
Individual / Group Exercise - 20 min
Q&A/Discussion - 15 min
Reflection - 5 min
Prerequisits:
No specific technical skills required
Bring Your Own Laptop
.png)