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 sessionPhishing, overlooked vulnerabilities and failed backups: learn from real incidents how companies end up in crisis.
A click on the wrong link. An overlooked vulnerability. A backup that fails when it matters. Drawing on real incidents, Alexander Haunhorst shows three typical paths that lead companies into crisis. Alongside preventing attacks, the central question is: what happens when defences fail?
How can security risks be identified before AI applications go live? Threat modeling through a practical agent example.
View sessionWhat 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 sessionExperience a simulated cyberattack, make decisions and understand the consequences.
View session