Practical AI Security Assessments Using OWASP AISVS

Join us for an insightful workshop led by Jim Manico, the project leader of the OWASP AI Security Verification Standard (AISVS). Discover how to effectively verify the security of AI systems through practical assessment scenarios using the OWASP AISVS.

What You'll Learn:

• Prompt Injection Defense: Understand how to defend against prompt injection attacks.
• Agentic Action Security: Explore security measures for autonomous agents.
• RAG/Vector Database Hardening: Learn about hardening techniques for databases.
• Output Safety Controls: Implement safety controls for AI outputs.

Participants will gain a solid understanding of how to:

• Scope an AI security assessment
• Select appropriate verification levels
• Apply AISVS requirements to LLM-based applications, autonomous agents, and MCP-connected tool ecosystems.

💻 Bring a laptop if you want to follow along with the practical exercises!

📍 Location: Las Vegas Convention Center, 3150 Paradise Rd, Las Vegas, NV 89109, USA