Expert Talk
What Could Go Wrong? Threat Modeling AI Before It Ships
How can security risks be identified before AI applications go live? Threat modeling through a practical agent example.
View sessionExpert Talk · Wed 25.11.
Unchecked trust boundaries: how attackers get into your network through plugins, MCP and agent frameworks
Where plugins, MCP servers and agent frameworks open trust boundaries that nobody has checked.
What to expect
Inside the session.
Christian Schleicher shows how attackers reach a company network through the extensions and interfaces of AI agents, and which checks close those paths. Description and time to follow.
- Format
- Expert Talk
- Day
- Wed 25.11.
- Time
- Exact session time to follow.
More from this day.
Expert Talk
Three Paths to Disaster – How Ransomware Brings Companies to Their Knees
Phishing, overlooked vulnerabilities and failed backups: learn from real incidents how companies end up in crisis.
View session
Expert Talk
When Your AI Agent Becomes an Insider Threat
What happens when an AI agent can use internal data and tools? Understand the risks, then put them to the test in “Roast My Agent”.
View session