AI Security Night Munich
🚀 AI Security Meetup Munich – Our First Event!
Hello everyone,
We’re excited to announce our very first AI Security Meetup in Munich, focused on building AI applications safely, securely, and reliably.
Join us for an evening of learning, networking, and discussions with two excellent speakers covering some of the most important security challenges facing AI today
Talk 1: Breaching LLM-Powered Applications – Overcoming Security and Privacy Challenges
As organizations rapidly adopt Large Language Models (LLMs), new security and privacy risks emerge alongside the opportunities they create.
In this session, we'll explore the security and data privacy challenges of AI applications powered by LLMs, including:
Prompt injection attacks
API key leakage
Data misuse and privacy concerns
How traditional security vulnerabilities impact LLM behavior
Practical strategies and best practices for building secure AI applications
Speaker: Brian Vermeer, Staff Developer Advocate at Snyk
Talk 2: SAIF 2.0 – Security Strategies for the Era of Autonomous AI Agents
The rise of large language models has made security a top priority for AI applications. However, while we are still in the process of securing static models, the next technological leap is already underway: the transition to autonomous AI agents. These systems don't just generate text; they also use tools, access APIs and make independent decisions.
In this talk, we analyse the Secure AI Framework (SAIF), developed by Google, and its evolution into SAIF 2.0. We will explain why conventional security approaches are ineffective with active AI systems and how robust agent infrastructures can be designed.
Key topics of the talk:
SAIF Foundations: An overview of the six pillars for secure AI ecosystems.
The leap to SAIF 2.0: Why agents need a new risk matrix.
Technical Deep Dive: Analysis of new attack vectors, such as indirect prompt injection via RAG data sources, and security risks in agents' long-term memory.
Governance in Practice: How the framework helps to develop “Secure by Design” AI applications and minimises risks through automated assessments.
This talk provides developers and security professionals with a clear roadmap for safely and responsibly unlocking the potential of AI agents in enterprises.
Speaker: Christian Fritz, Software Architect, QAware
Agenda
6:00 PM – Doors open
6:00–6:30 PM – Food & drinks 🍕🍻
6:30 PM – Talks begin
8:00 PM – Talks conclude
8:00 PM onwards – Networking & social time
We look forward to seeing you in Munich for an evening dedicated to AI security, practical insights, and great conversations with fellow AI builders and security professionals. Expect insightful talks from industry experts, practical takeaways you can apply to your own AI projects, great company from the local tech community, and of course plenty of food and drinks throughout the evening. Whether you're already building AI-powered applications or simply curious about the latest developments in AI security, we'd love to have you join us. 🚀